{"id":2416,"date":"2026-09-22T07:10:43","date_gmt":"2026-09-21T22:10:43","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/09\/22\/mimo-v2-6-distill-qwen-9b-gguf\/"},"modified":"2026-11-09T07:12:40","modified_gmt":"2026-11-08T22:12:40","slug":"mimo-v2-6-distill-qwen-9b-gguf","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/22\/mimo-v2-6-distill-qwen-9b-gguf\/","title":{"rendered":"MiMo-V2.6-Distill-Qwen-9B-GGUF: Our Test Answers, 12GB+ VRAM"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/huggingface.co\/ggml-org\/MiMo-V2.6-Distill-Qwen-9B-GGUF\">ggml-org\/MiMo-V2.6-Distill-Qwen-9B-GGUF<\/a><\/td>\n<\/tr>\n<tr>\n<td>Family guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-xiaomimimo-mimo-v2-6-en\/\">MiMo-V2.6 guide (4 articles)<\/a><\/td>\n<\/tr>\n<tr>\n<td>Publisher guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-alibaba-en\/\">Alibaba (Qwen): models and licenses<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-09-22<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>mit<\/td>\n<\/tr>\n<tr>\n<td>Formats<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF<\/a><\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<p><!-- lmw:lab-summary --><\/p>\n<p><strong>What we checked ourselves<\/strong><\/p>\n<ul>\n<li>Ran <code>MiMo-V2.6-Distill-Qwen-9B-Q8_0.gguf<\/code> (Q8_0) on our CPU-only server (Neoverse-N1, 3 threads, llama.cpp b11223): generation at 3.7 tokens\/s (a CPU figure, not a GPU speed).<\/li>\n<li>Its answers to our fixed Japanese questions are shown verbatim below.<\/li>\n<li>It needs about 21% fewer tokens than the Qwen3 tokenizer for the same Japanese text, so about 1.26\u00d7 as much Japanese fits in the same context length, and generation is faster per character.<\/li>\n<\/ul>\n<p>Details and conditions are in \u201cOur Own Measurements\u201d below.<\/p>\n<p><!-- \/lmw:lab-summary --><\/p>\n<h2>Overview<\/h2>\n<p>On September 21, 2026, ggml-org released the GGUF version of &#8220;MiMo-V2.6-Distill-Qwen-9B&#8221;, an agent-oriented model developed by Xiaomi MiMo. Based on Qwen3.5-9B, this 9.4B parameter model has undergone distillation and supervised fine-tuning (SFT) using datasets generated by MiMo. It is designed to target four main domains: coding, general agent tasks, visual coding, and cybersecurity.<\/p>\n<p>According to the model card, it was released as an open research starting point for agentic reinforcement learning. The GGUF distribution also includes a Q8_0 mmproj file for the vision encoder, providing support for multimodal tasks. Readers can try out this agent-specialized model in GGUF-compatible environments such as llama.cpp and Ollama.<\/p>\n<h2>Specifications<\/h2>\n<ul>\n<li>Parameters: 9.4B<\/li>\n<li>Architecture: Qwen3_5ForConditionalGeneration (Qwen 3.5)<\/li>\n<\/ul>\n<h2>Performance<\/h2>\n<p>The performance evaluations shown below are figures based on the technical report of the original model (XiaomiMiMo\/MiMo-V2.6-Distill-Qwen-9B) released by Xiaomi MiMo, featuring comparisons with the base model Qwen3.5-9B. Note that in the GGUF quantization format, these figures may vary slightly due to the quantization process.<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Domain<\/th>\n<th>Benchmark<\/th>\n<th>Metric<\/th>\n<th style=\"text-align: right;\">Qwen3.5-9B<\/th>\n<th style=\"text-align: right;\">MiMo-V2.6-Distill-Qwen-9B (SFT)<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Code<\/td>\n<td>SWE Verified<\/td>\n<td>avg@3<\/td>\n<td style=\"text-align: right;\">60.0<\/td>\n<td style=\"text-align: right;\">61.1<\/td>\n<\/tr>\n<tr>\n<td>Code<\/td>\n<td>SWE Pro<\/td>\n<td>avg@3<\/td>\n<td style=\"text-align: right;\">32.0<\/td>\n<td style=\"text-align: right;\">44.6<\/td>\n<\/tr>\n<tr>\n<td>Code<\/td>\n<td>MiMo Code (mini)\u2020<\/td>\n<td>avg@3<\/td>\n<td style=\"text-align: right;\">19.5<\/td>\n<td style=\"text-align: right;\">51.6<\/td>\n<\/tr>\n<tr>\n<td>Cyber<\/td>\n<td>MiMo Cyber (mini)\u2020<\/td>\n<td>avg@3<\/td>\n<td style=\"text-align: right;\">5.7<\/td>\n<td style=\"text-align: right;\">31.3<\/td>\n<\/tr>\n<tr>\n<td>General<\/td>\n<td>AutomationBench v1.0.6<\/td>\n<td>avg@1<\/td>\n<td style=\"text-align: right;\">5.0<\/td>\n<td style=\"text-align: right;\">30.3<\/td>\n<\/tr>\n<tr>\n<td>General<\/td>\n<td>Terminal Bench 2.1<\/td>\n<td>avg@1<\/td>\n<td style=\"text-align: right;\">27.0<\/td>\n<td style=\"text-align: right;\">37.1<\/td>\n<\/tr>\n<tr>\n<td>General<\/td>\n<td>Toolathlon-Verified<\/td>\n<td>avg@1<\/td>\n<td style=\"text-align: right;\">25.9<\/td>\n<td style=\"text-align: right;\">35.2<\/td>\n<\/tr>\n<tr>\n<td>General<\/td>\n<td>OfficeQA<\/td>\n<td>avg@1<\/td>\n<td style=\"text-align: right;\">9.0<\/td>\n<td style=\"text-align: right;\">19.5<\/td>\n<\/tr>\n<tr>\n<td>General<\/td>\n<td>JobBench<\/td>\n<td>avg@1<\/td>\n<td style=\"text-align: right;\">2.6<\/td>\n<td style=\"text-align: right;\">18.3<\/td>\n<\/tr>\n<tr>\n<td>General<\/td>\n<td>MiMo General (mini)\u2020<\/td>\n<td>avg@1<\/td>\n<td style=\"text-align: right;\">28.5<\/td>\n<td style=\"text-align: right;\">62.2<\/td>\n<\/tr>\n<tr>\n<td>Visual<\/td>\n<td>MiMo Visual Coding (mini)\u2020<\/td>\n<td>avg@1<\/td>\n<td style=\"text-align: right;\">61.7<\/td>\n<td style=\"text-align: right;\">64.0<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>\u2020 Figures from internal evaluation sets<\/p>\n<p>From the publisher&#8217;s measurement results, it can be seen that this model improves scores across almost all evaluation items compared to the base model Qwen3.5-9B. Notably, the score increase on &#8220;Terminal Bench 2.1&#8221; from 27.0 to 37.1 is worth highlighting. Terminal-Bench is an indicator that measures practical ability as an agent\u2014whether it can actually execute commands on a terminal and see a given task through to completion\u2014suggesting that this model is strong in tasks involving terminal operations.<\/p>\n<p>In addition, dramatic improvements are seen in specific specialized areas, such as moving from 32.0 to 44.6 on SWE Pro, a challenging benchmark in the coding field, and from 5.7 to 31.3 on the internal cyber security evaluation (MiMo Cyber mini). On the other hand, items like SWE Verified showed only a marginal improvement from 60.0 to 61.1, indicating that it does not show a uniformly overwhelming difference across all coding tasks. Overall, it can be said to be a model that demonstrates particular strength in areas requiring agentic behavior, such as automation (AutomationBench) and tool use (Toolathlon-Verified).<\/p>\n<p>For reference, the composition of the data used to train this model is reported as follows. Out of a total 77.4B tokens, loss-bearing tokens contributing to learning account for 27.2B tokens.<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Domain<\/th>\n<th style=\"text-align: right;\">Total tokens (B)<\/th>\n<th style=\"text-align: right;\">Token share (%)<\/th>\n<th style=\"text-align: right;\">Loss-bearing tokens (B)<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Code<\/td>\n<td style=\"text-align: right;\">23.2<\/td>\n<td style=\"text-align: right;\">29.9<\/td>\n<td style=\"text-align: right;\">7.3<\/td>\n<\/tr>\n<tr>\n<td>Cyber<\/td>\n<td style=\"text-align: right;\">11.0<\/td>\n<td style=\"text-align: right;\">14.2<\/td>\n<td style=\"text-align: right;\">4.8<\/td>\n<\/tr>\n<tr>\n<td>General<\/td>\n<td style=\"text-align: right;\">22.0<\/td>\n<td style=\"text-align: right;\">28.5<\/td>\n<td style=\"text-align: right;\">5.7<\/td>\n<\/tr>\n<tr>\n<td>Visual<\/td>\n<td style=\"text-align: right;\">21.2<\/td>\n<td style=\"text-align: right;\">27.4<\/td>\n<td style=\"text-align: right;\">9.4<\/td>\n<\/tr>\n<tr>\n<td><strong>Total<\/strong><\/td>\n<td style=\"text-align: right;\"><strong>77.4<\/strong><\/td>\n<td style=\"text-align: right;\"><strong>100.0<\/strong><\/td>\n<td style=\"text-align: right;\"><strong>27.2<\/strong><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h2>Strengths and Use Cases<\/h2>\n<p>The greatest identity of this model lies in its advanced autonomy as an &#8220;agent&#8221; that goes beyond mere text generation. As developer Xiaomi MiMo positions this model as a research foundation for agentic reinforcement learning, it excels in the ability to interpret complex instructions, break them down into concrete steps, and execute them. By applying supervised fine-tuning (SFT) using high-quality datasets generated by MiMo to the base model Qwen3.5-9B, it has achieved dramatic evolution in specific specialized domains.<\/p>\n<p>Particularly noteworthy is its adaptability to tasks involving terminal operations. The high score on &#8220;Terminal-Bench 2.1&#8221; mentioned in the performance section indicates that this model can accurately simulate or direct command-line operations in local or server environments. It holds the potential to directly support engineers&#8217; daily workflows, such as creating system administration automation scripts, building complex deployment procedures, and even interactive system troubleshooting. Regarding tool-use, as indicated by the score improvement in Toolathlon-Verified, its capability to properly invoke external tools to complete tasks has been enhanced.<\/p>\n<p>Furthermore, the model is designed to explicitly output a &#8220;thinking&#8221; process. This means the model takes internal reasoning steps before producing a final answer, which has the effect of preventing logical breakdowns, especially in mathematical calculations and complex algorithm construction. Users can enable the thinking function via API to check <code>reasoning_content<\/code> and see what logical progression the model took to reach a conclusion. This transparency is extremely useful in debugging tasks or critical scenes where humans need to verify the grounds for the model&#8217;s decisions.<\/p>\n<p>The breadth of supported domains and specialization is also noteworthy. The training data strategically blends the following four areas:<\/p>\n<ul>\n<li><strong>Fusion of Coding and Vision<\/strong>: Through the enhancement of the &#8220;Visual Coding&#8221; domain, it supports development tasks starting from visual information, such as reading website screenshots or UI blueprints and generating HTML\/CSS or React code to realize them. 27.4% of the training data is allocated to visual-related content (Visual), expecting advanced coordination between image recognition and code generation.<\/li>\n<li><strong>Cybersecurity<\/strong>: Cybersecurity-related data amounting to 11 billion tokens (11.0B tokens) has been fed into the model. This anticipates applications in highly specialized security tasks that are difficult for general LLMs, such as assisting with vulnerability diagnostics, analyzing security logs, and creating penetration testing scenarios.<\/li>\n<li><strong>General Agent Tasks<\/strong>: As shown by score improvements in benchmarks like OfficeQA and JobBench, practical agent functions such as office automation and job process management have been enhanced.<\/li>\n<\/ul>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 9.4B parameters (taken from the base model XiaomiMiMo\/MiMo-V2.6-Distill-Qwen-9B)<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Your VRAM<\/th>\n<th>Quantization<\/th>\n<th>File size<\/th>\n<th>Est. memory needed<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>12GB (RTX 4070 \/ 3060 12GB, etc.)<\/td>\n<td>Q8_0<\/td>\n<td>8.9GB<\/td>\n<td>10.6GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model&#8217;s authors. Compare with other models in our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-en\/\">VRAM quick reference<\/a>. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:hardware --><\/p>\n<p><!-- lmw:runnability --><\/p>\n<h2>Can You Run It Locally?<\/h2>\n<p><strong>Runs in Ollama, LM Studio and llama.cpp as-is.<\/strong><\/p>\n<p>It is distributed in GGUF, so no conversion is needed.<\/p>\n<p><strong>License \u2014 <code>mit<\/code> (Commercial use allowed):<\/strong> Permits commercial use, modification and redistribution, provided the copyright notice and license text are retained.<\/p>\n<p><strong>Compression:<\/strong> the Q8_0 build measures 8.12 bits per weight \u2014 about 51% the size of the original 16-bit weights, calculated by this site from the actual file sizes.<\/p>\n<p><em>Compiled by this site&#8217;s code from the published formats, converted builds we have found, and each engine&#8217;s own model registry. &#8220;Not found&#8221; means we have not seen such a build, not that none exists. License summaries are not legal advice \u2014 check the publisher&#8217;s original terms before relying on them.<\/em><\/p>\n<p><!-- \/lmw:runnability --><\/p>\n<p><!-- lmw:lab --><\/p>\n<h2>Our Own Measurements<\/h2>\n<p>Values we measured ourselves on our server (no GPU) by actually reading and running this model&#8217;s files \u2014 not figures copied from the model card. How we measure, and the results for every model: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/observations-en\/\">Our Measurements<\/a>.<\/p>\n<h3>What We Found<\/h3>\n<p>When running the Q8_0 file of MiMo-V2.6-Distill-Qwen-9B-GGUF on a Neoverse-N1 CPU with 3 threads, the generation speed was 3.69 tokens per second, which translates to 6.8 Japanese characters per second. This speed is close to Cloudflare_clef-flash at 3.85 tokens per second measured under the same conditions, and it consumed 14.8GB of memory at peak. Additionally, the number of tokens per 1,000 Japanese characters is 546, allowing it to process Japanese more efficiently with fewer tokens compared to 688 for Qwen3.<\/p>\n<p>For the five Japanese questions, answers were obtained for all of them without hitting the upper limit truncation, repeating the same lines, or mixing in thinking processes. In the summarization of an article of about 1,200 characters, it outputted the exact three sentences as instructed, and in the shopping word problem, it correctly answered 280 yen. Furthermore, in image reading, it correctly answered the busiest day of the week, the 260 visitors on Saturday, and the weekday total of 635 visitors in the graph of visitors by day of the week.<\/p>\n<p>On the other hand, in the knowledge question about listing prefectures not facing the ocean, while it listed 3 out of the 8 prefectures not facing the ocean, it mistakenly included 11 prefectures that actually do face the ocean. In drafting a polite email to a business partner, an answer was successfully generated, but two English words were mixed into the Japanese response. Overall, while calculations and data reading were handled accurately, challenges remained in accurately grasping geographical knowledge.<\/p>\n<h3>Japanese Token Efficiency<\/h3>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Tokenizer<\/th>\n<th>Tokens per 1,000 Japanese characters<\/th>\n<th>Ratio to the same text in English<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><strong>This model<\/strong><\/td>\n<td><strong>546<\/strong><\/td>\n<td><strong>0.99\u00d7<\/strong><\/td>\n<\/tr>\n<tr>\n<td>Qwen3<\/td>\n<td>688<\/td>\n<td>1.26\u00d7<\/td>\n<\/tr>\n<tr>\n<td>Llama 3.2<\/td>\n<td>744<\/td>\n<td>1.36\u00d7<\/td>\n<\/tr>\n<tr>\n<td>Gemma 3<\/td>\n<td>564<\/td>\n<td>1.03\u00d7<\/td>\n<\/tr>\n<tr>\n<td>gpt-oss<\/td>\n<td>795<\/td>\n<td>1.45\u00d7<\/td>\n<\/tr>\n<tr>\n<td>LLM-jp-3<\/td>\n<td>497<\/td>\n<td>0.85\u00d7<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>It needs about 21% fewer tokens than the Qwen3 tokenizer for the same Japanese text, so about 1.26\u00d7 as much Japanese fits in the same context length, and generation is faster per character.<\/p>\n<p>Counted with the <code>tokenizer.json<\/code> of <a href=\"https:\/\/huggingface.co\/XiaomiMiMo\/MiMo-V2.6-Distill-Qwen-9B\">XiaomiMiMo\/MiMo-V2.6-Distill-Qwen-9B<\/a> on a fixed text we wrote ourselves (876 Japanese characters across news, conversation, technical docs, a formal email, travel writing and a recipe) and its English translation. Fewer tokens mean more Japanese fits in the context window.<\/p>\n<h3>Inside the GGUF File<\/h3>\n<p>File: <a href=\"https:\/\/huggingface.co\/ggml-org\/MiMo-V2.6-Distill-Qwen-9B-GGUF\/blob\/main\/MiMo-V2.6-Distill-Qwen-9B-Q8_0.gguf\">MiMo-V2.6-Distill-Qwen-9B-Q8_0.gguf<\/a> (8.87GB, <code>Q8_0<\/code>). We read only the header (metadata) of the file, not the weights.<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Architecture (as named in the GGUF)<\/td>\n<td><code>qwen35<\/code><\/td>\n<\/tr>\n<tr>\n<td>Maximum trained context length<\/td>\n<td>262,144 tokens<\/td>\n<\/tr>\n<tr>\n<td>Layers<\/td>\n<td>32<\/td>\n<\/tr>\n<tr>\n<td>Vocabulary size<\/td>\n<td>248,320<\/td>\n<\/tr>\n<tr>\n<td>Chat template<\/td>\n<td>Included (mentions tool calls, has a thinking switch)<\/td>\n<\/tr>\n<tr>\n<td>imatrix<\/td>\n<td>Not recorded in the file<\/td>\n<\/tr>\n<tr>\n<td>Weight types (share of parameters)<\/td>\n<td>Q8_0 100.0% \/ F32 0.0%<\/td>\n<\/tr>\n<tr>\n<td>Average bits per weight<\/td>\n<td>8.50 bits<\/td>\n<\/tr>\n<tr>\n<td>Embedding \/ output layer type<\/td>\n<td>Q8_0 \/ Q8_0<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>The quant name in the file name describes the file as a whole; in practice layers mix several types. The average bits per weight is the measured file data divided by the number of weights.<\/p>\n<h3>Running It on a CPU Only<\/h3>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Result<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Prompt processing (512 tokens)<\/td>\n<td>16.1 tokens\/s<\/td>\n<\/tr>\n<tr>\n<td>Generation (128 tokens)<\/td>\n<td>3.7 tokens\/s<\/td>\n<\/tr>\n<tr>\n<td>Generation in Japanese characters<\/td>\n<td>about 6.8 characters\/s<\/td>\n<\/tr>\n<tr>\n<td>Peak memory (context 4,096 tokens)<\/td>\n<td>14.8GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>Conditions: Neoverse-N1, 3 threads, no GPU, llama.cpp b11223, <code>Q8_0<\/code> (8.87GB) from <a href=\"https:\/\/huggingface.co\/ggml-org\/MiMo-V2.6-Distill-Qwen-9B-GGUF\">ggml-org\/MiMo-V2.6-Distill-Qwen-9B-GGUF<\/a>, measured 2026-09-30 (JST). This repository offers no 4-bit file, so we measured the <code>Q8_0<\/code> file it provides. Other models measured under the same conditions (closest in file size):<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Quant<\/th>\n<th>File size<\/th>\n<th>Generation<\/th>\n<th>In Japanese<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/26\/qwen3-8-27b-overview-specs-performance\/\">Qwen3.8-27B<\/a><\/td>\n<td><code>IQ3_XXS<\/code><\/td>\n<td>10.18GB<\/td>\n<td>0.6 tokens\/s<\/td>\n<td>1.2 chars\/s<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/28\/xing4-0-29b-a4b-china-telecom\/\">Xing4.0-29B-A4B<\/a><\/td>\n<td><code>IQ2_M<\/code><\/td>\n<td>10.99GB<\/td>\n<td>4.5 tokens\/s<\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/12\/signal-3-8-27b-gguf-overview\/\">Signal-3.8-27B<\/a><\/td>\n<td><code>IQ3_XXS<\/code><\/td>\n<td>11.39GB<\/td>\n<td>0.6 tokens\/s<\/td>\n<td>1.2 chars\/s<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/11\/pantheon-reasoning-26b-gguf\/\">Gryphe_Pantheon-Reasoning-26B-A4B-1.1-V2<\/a><\/td>\n<td><code>Q3_K_S<\/code><\/td>\n<td>12.26GB<\/td>\n<td>6.2 tokens\/s<\/td>\n<td>11.0 chars\/s<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>Peak memory includes the model file mapped into memory (mmap). A PC with a GPU will be much faster; these figures are a guide for CPU-only machines such as mini PCs and ARM boards.<\/p>\n<h3>Answers to Our Japanese Questions (Verbatim)<\/h3>\n<p>We ask every model the same five questions in Japanese under the conditions above (temperature 0, thinking turned off where the chat template allows it, up to 1024 tokens) and publish the answers unedited. We do not grade them; where a question has a single correct answer, we show it for comparison.<\/p>\n<p><strong>Summarization<\/strong><\/p>\n<blockquote>\n<p>\u6b21\u306e\u8a18\u4e8b\u30923\u6587\u3067\u8981\u7d04\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n<p>\u307f\u3069\u308a\u5e02\u306f\u4eca\u5e74\u306e\u6625\u3001\u5e02\u5185\u306b\u4e09\u3064\u3042\u308b\u516c\u7acb\u56f3\u66f8\u9928\u306e\u3046\u3061\u6700\u3082\u53e4\u3044\u4e2d\u592e\u56f3\u66f8\u9928\u306e\u6539\u4fee\u3092\u7d42\u3048\u3001\u5341\u6708\u4e00\u65e5\u306b\u518d\u958b\u9928\u3057\u305f\u3002\u6539\u4fee\u306f\u7d04\u4e00\u5e74\u534a\u306b\u308f\u305f\u308a\u3001\u7dcf\u4e8b\u696d\u8cbb\u306f\u7d04\u5341\u4e8c\u5104\u5186\u3002\u3053\u306e\u3046\u3061\u7d04\u56db\u5104\u5186\u306f\u56fd\u306e\u88dc\u52a9\u91d1\u3067\u307e\u304b\u306a\u308f\u308c\u305f\u3002<\/p>\n<p>\u6700\u5927\u306e\u5909\u5316\u306f\u3001\u95b2\u89a7\u5e2d\u306e\u914d\u7f6e\u3067\u3042\u308b\u3002\u4ee5\u524d\u306f\u9928\u5185\u306e\u5ea7\u5e2d\u306e\u5927\u534a\u304c\u5b66\u7fd2\u7528\u306e\u673a\u3067\u3001\u8a66\u9a13\u671f\u9593\u306b\u306a\u308b\u3068\u4e2d\u9ad8\u751f\u3067\u57cb\u307e\u308a\u3001\u9ad8\u9f62\u306e\u5229\u7528\u8005\u3084\u5c0f\u3055\u306a\u5b50\u3069\u3082\u9023\u308c\u304c\u5ea7\u308c\u306a\u3044\u3068\u3044\u3046\u82e6\u60c5\u304c\u6bce\u5e74\u5bc4\u305b\u3089\u308c\u3066\u3044\u305f\u3002\u6539\u4fee\u5f8c\u306f\u5ea7\u5e2d\u6570\u3092\u767e\u4e8c\u5341\u5e2d\u304b\u3089\u4e8c\u767e\u5e2d\u306b\u5897\u3084\u3057\u305f\u3046\u3048\u3067\u3001\u5b66\u7fd2\u7528\u306e\u673a\u3092\u4e09\u968e\u306b\u307e\u3068\u3081\u3001\u4e00\u968e\u306f\u4f1a\u8a71\u304c\u3067\u304d\u308b\u300c\u306b\u304e\u308f\u3044\u30d5\u30ed\u30a2\u300d\u3001\u4e8c\u968e\u306f\u9759\u304b\u306b\u672c\u3092\u8aad\u3080\u300c\u95b2\u89a7\u30d5\u30ed\u30a2\u300d\u306b\u5206\u3051\u305f\u3002\u4e00\u968e\u306b\u306f\u4e88\u7d04\u5236\u306e\u30b0\u30eb\u30fc\u30d7\u5b66\u7fd2\u5ba4\u304c\u56db\u5ba4\u3068\u3001\u98f2\u307f\u7269\u3092\u6301\u3061\u8fbc\u3081\u308b\u30ab\u30d5\u30a7\u30b9\u30da\u30fc\u30b9\u3082\u8a2d\u3051\u3089\u308c\u305f\u3002<\/p>\n<p>\u8535\u66f8\u306e\u9762\u3067\u3082\u898b\u76f4\u3057\u304c\u9032\u3093\u3060\u3002\u8cb8\u51fa\u306e\u5c11\u306a\u3044\u53e4\u3044\u8cc7\u6599\u7d04\u4e09\u4e07\u518a\u3092\u5e02\u5185\u306e\u4ed6\u306e\u9928\u3084\u4fdd\u5b58\u66f8\u5eab\u306b\u79fb\u3057\u3001\u4ee3\u308f\u308a\u306b\u5b50\u3069\u3082\u5411\u3051\u306e\u7d75\u672c\u3068\u3001\u4ecb\u8b77\u30fb\u5b50\u80b2\u3066\u30fb\u4ed5\u4e8b\u63a2\u3057\u3068\u3044\u3063\u305f\u66ae\u3089\u3057\u306b\u95a2\u308f\u308b\u5b9f\u7528\u66f8\u3092\u7d04\u4e00\u4e07\u4e94\u5343\u518a\u5897\u3084\u3057\u305f\u3002\u96fb\u5b50\u66f8\u7c4d\u306e\u8cb8\u51fa\u30b5\u30fc\u30d3\u30b9\u3082\u59cb\u307e\u308a\u3001\u5229\u7528\u767b\u9332\u3092\u3059\u308c\u3070\u81ea\u5b85\u304b\u3089\u4e00\u5ea6\u306b\u4e09\u518a\u307e\u3067\u3001\u4e8c\u9031\u9593\u501f\u308a\u3089\u308c\u308b\u3002<\/p>\n<p>\u5efa\u7269\u305d\u306e\u3082\u306e\u306b\u3082\u624b\u304c\u5165\u3063\u305f\u3002\u7bc9\u56db\u5341\u5e74\u3092\u8d85\u3048\u3066\u3044\u305f\u7a7a\u8abf\u8a2d\u5099\u3092\u5165\u308c\u66ff\u3048\u3001\u5c4b\u4e0a\u306b\u306f\u592a\u967d\u5149\u30d1\u30cd\u30eb\u3092\u8a2d\u7f6e\u3057\u3066\u3001\u9928\u5185\u3067\u4f7f\u3046\u96fb\u529b\u306e\u7d04\u4e8c\u5272\u3092\u307e\u304b\u306a\u3048\u308b\u3088\u3046\u306b\u3057\u305f\u3002\u8eca\u3044\u3059\u306e\u5229\u7528\u8005\u304b\u3089\u8981\u671b\u306e\u591a\u304b\u3063\u305f\u30a8\u30ec\u30d9\u30fc\u30bf\u30fc\u306f\u4e00\u57fa\u304b\u3089\u4e8c\u57fa\u306b\u5897\u3048\u3001\u66f8\u67b6\u306e\u9593\u306e\u901a\u8def\u3082\u4ee5\u524d\u3088\u308a\u4e09\u5341\u30bb\u30f3\u30c1\u5e83\u3052\u3089\u308c\u305f\u3002\u5165\u53e3\u306b\u306f\u6bb5\u5dee\u306e\u306a\u3044\u30b9\u30ed\u30fc\u30d7\u304c\u65b0\u305f\u306b\u8a2d\u3051\u3089\u308c\u3001\u6388\u4e73\u5ba4\u3068\u591a\u76ee\u7684\u30c8\u30a4\u30ec\u3082\u5404\u968e\u306b\u4e00\u3064\u305a\u3064\u7f6e\u304b\u308c\u305f\u3002<\/p>\n<p>\u4e00\u65b9\u3067\u8ab2\u984c\u3082\u6b8b\u308b\u3002\u99d0\u8eca\u5834\u306f\u6539\u4fee\u524d\u3068\u540c\u3058\u56db\u5341\u53f0\u306e\u307e\u307e\u3067\u3001\u9031\u672b\u306b\u306f\u8fd1\u304f\u306e\u9053\u8def\u306b\u9806\u756a\u5f85\u3061\u306e\u8eca\u304c\u4e26\u3093\u3060\u3002\u5e02\u306f\u96a3\u63a5\u3059\u308b\u5e02\u6709\u5730\u3092\u81e8\u6642\u99d0\u8eca\u5834\u3068\u3057\u3066\u958b\u653e\u3057\u305f\u304c\u3001\u6052\u4e45\u7684\u306a\u5bfe\u7b56\u306f\u6c7a\u307e\u3063\u3066\u3044\u306a\u3044\u3002\u307e\u305f\u3001\u958b\u9928\u6642\u9593\u3092\u5e73\u65e5\u306e\u591c\u4e5d\u6642\u307e\u3067\u5ef6\u3070\u3057\u305f\u3053\u3068\u3067\u8077\u54e1\u306e\u8ca0\u62c5\u304c\u5897\u3048\u3066\u304a\u308a\u3001\u8077\u54e1\u56e3\u4f53\u306f\u4eba\u54e1\u306e\u8ffd\u52a0\u3092\u6c42\u3081\u3066\u3044\u308b\u3002<\/p>\n<p>\u5229\u7528\u8005\u306e\u53d7\u3051\u6b62\u3081\u306f\u304a\u304a\u3080\u306d\u597d\u610f\u7684\u3060\u3002\u9031\u306b\u4e8c\u5ea6\u3001\u5b6b\u3092\u9023\u308c\u3066\u6765\u308b\u3068\u3044\u3046\u4e03\u5341\u4ee3\u306e\u5973\u6027\u306f\u300c\u524d\u306f\u5b50\u3069\u3082\u304c\u58f0\u3092\u51fa\u3059\u3068\u5468\u308a\u306e\u76ee\u304c\u6c17\u306b\u306a\u3063\u305f\u304c\u3001\u4e00\u968e\u306a\u3089\u6c17\u517c\u306d\u306a\u304f\u7d75\u672c\u3092\u8aad\u3093\u3067\u3042\u3052\u3089\u308c\u308b\u300d\u3068\u8a71\u3059\u3002\u4e00\u65b9\u3001\u53d7\u9a13\u3092\u63a7\u3048\u305f\u9ad8\u6821\u751f\u306e\u4e2d\u306b\u306f\u300c\u5b66\u7fd2\u5e2d\u304c\u4e09\u968e\u3060\u3051\u306b\u306a\u308a\u3001\u5915\u65b9\u306f\u3059\u3050\u306b\u6e80\u5e2d\u306b\u306a\u308b\u300d\u3068\u4e0d\u6e80\u3092\u6f0f\u3089\u3059\u4eba\u3082\u3044\u308b\u3002\u56f3\u66f8\u9928\u306f\u3001\u5b66\u7fd2\u5e2d\u306e\u7a7a\u304d\u72b6\u6cc1\u3092\u30db\u30fc\u30e0\u30da\u30fc\u30b8\u3067\u78ba\u8a8d\u3067\u304d\u308b\u4ed5\u7d44\u307f\u3092\u5e74\u5185\u306b\u5c0e\u5165\u3059\u308b\u4e88\u5b9a\u3060\u3002<\/p>\n<p>\u518d\u958b\u9928\u306b\u5408\u308f\u305b\u3066\u3001\u50ac\u3057\u3082\u5897\u3048\u305f\u3002\u6bce\u9031\u571f\u66dc\u306e\u5348\u524d\u306b\u306f\u8aad\u307f\u805e\u304b\u305b\u4f1a\u3001\u6708\u306b\u4e00\u5ea6\u306f\u5730\u5143\u306e\u8fb2\u5bb6\u3084\u5546\u5e97\u4e3b\u3092\u8b1b\u5e2b\u306b\u62db\u304f\u300c\u307e\u3061\u306e\u5148\u751f\u300d\u8b1b\u5ea7\u304c\u958b\u304b\u308c\u308b\u3002\u5341\u4e00\u6708\u306b\u306f\u3001\u5e02\u5185\u306e\u4e2d\u5b66\u751f\u304c\u9078\u3093\u3060\u672c\u3092\u7d39\u4ecb\u3059\u308b\u5c55\u793a\u3082\u4e88\u5b9a\u3055\u308c\u3066\u3044\u308b\u3002<\/p>\n<p>\u9928\u9577\u306e\u5c71\u672c\u548c\u5b50\u3055\u3093\u306f\u300c\u672c\u3092\u501f\u308a\u308b\u5834\u6240\u304b\u3089\u3001\u4eba\u304c\u96c6\u307e\u3063\u3066\u904e\u3054\u3059\u5834\u6240\u3078\u5909\u3048\u305f\u304b\u3063\u305f\u3002\u518d\u958b\u9928\u304b\u3089\u306e\u4e00\u304b\u6708\u3067\u6765\u9928\u8005\u306f\u4ee5\u524d\u306e\u4e00\u30fb\u516b\u500d\u306b\u306a\u3063\u305f\u300d\u3068\u8a71\u3059\u3002\u5e02\u306f\u6765\u5e74\u5ea6\u3001\u6b8b\u308b\u4e8c\u3064\u306e\u56f3\u66f8\u9928\u306b\u3064\u3044\u3066\u3082\u5229\u7528\u8005\u3078\u306e\u805e\u304d\u53d6\u308a\u3092\u884c\u3044\u3001\u6539\u4fee\u306e\u5fc5\u8981\u6027\u3092\u691c\u8a0e\u3059\u308b\u65b9\u91dd\u3060\u3002<\/p>\n<\/blockquote>\n<p><em>(Summarize the following article in three sentences. (The article, about 1,200 Japanese characters, describes the renovation and reopening of a city&#8217;s central library: the budget, the new floor layout and seating, changes to the collection and e-book lending, building and accessibility work, remaining issues such as parking and staff workload, users&#8217; reactions, new events, and the city&#8217;s next steps.))<\/em><\/p>\n<pre><code class=\"language-text\">\u307f\u3069\u308a\u5e02\u306e\u4e2d\u592e\u56f3\u66f8\u9928\u306f\u7d04\u4e00\u5e74\u534a\u3001\u7dcf\u4e8b\u696d\u8cbb\u7d0412\u5104\u5186\uff08\u56fd\u88dc\u52a9\u7d044\u5104\u5186\uff09\u3092\u304b\u3051\u3066\u6539\u4fee\u3057\u300110\u67081\u65e5\u306b\u300c\u4eba\u304c\u96c6\u307e\u308b\u5834\u6240\u300d\u3078\u3068\u59ff\u3092\u5909\u3048\u3066\u518d\u958b\u9928\u3057\u307e\u3057\u305f\u3002\u95b2\u89a7\u5e2d\u309220\u5e2d\u5897\u3084\u3057\u3066\u968e\u3054\u3068\u306b\u7528\u9014\u3092\u5206\u3051\u3001\u8535\u66f8\u3084\u8a2d\u5099\u3082\u5237\u65b0\u3057\u305f\u4e00\u65b9\u3001\u99d0\u8eca\u5834\u306e\u4e0d\u8db3\u3084\u8077\u54e1\u8ca0\u62c5\u306e\u5897\u5927\u3068\u3044\u3063\u305f\u8ab2\u984c\u3082\u6b8b\u3063\u3066\u3044\u307e\u3059\u3002\u9928\u9577\u306f\u518d\u958b\u9928\u4e00\u304b\u6708\u3067\u6765\u9928\u8005\u304c1.8\u500d\u306b\u306a\u3063\u305f\u3068\u5831\u544a\u3057\u3001\u5e02\u306f\u6b8b\u308b\u4e8c\u9928\u306e\u6539\u4fee\u691c\u8a0e\u3078\u9032\u3081\u308b\u65b9\u91dd\u3067\u3059\u3002\n<\/code><\/pre>\n<p><strong>Formal business email<\/strong><\/p>\n<blockquote>\n<p>\u53d6\u5f15\u5148\u306e\u62c5\u5f53\u8005\u306b\u3001\u6765\u9031\u706b\u66dc\u65e5\u306e\u6253\u3061\u5408\u308f\u305b\u3092\u6c34\u66dc\u65e5\u306b\u5909\u66f4\u3057\u3066\u307b\u3057\u3044\u3068\u304a\u9858\u3044\u3059\u308b\u30e1\u30fc\u30eb\u3092\u3001\u4e01\u5be7\u306a\u656c\u8a9e\u3067\u66f8\u3044\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/blockquote>\n<p><em>(Write an email in polite Japanese (keigo) asking a client&#8217;s contact person to move next Tuesday&#8217;s meeting to Wednesday.)<\/em><\/p>\n<pre><code class=\"language-text\">\u4ef6\u540d\uff1a\u3010\u3054\u76f8\u8ac7\u3011\u6765\u9031\u706b\u66dc\u65e5\u306e\u6253\u3061\u5408\u308f\u305b\u65e5\u7a0b\u5909\u66f4\u306e\u3054\u4f9d\u983c\uff08\u3007\u3007\u682a\u5f0f\u4f1a\u793e \u5fa1\u4e2d\uff09\n\n\u3007\u3007\u682a\u5f0f\u4f1a\u793e\n\u5fa1\u4e2d\n\n\u5e73\u7d20\u3088\u308a\u683c\u5225\u306e\u3054\u9ad8\u914d\u3092\u8cdc\u308a\u3001\u539a\u304f\u5fa1\u793c\u7533\u3057\u4e0a\u3052\u307e\u3059\u3002\n\n\u3053\u306e\u305f\u3073\u3001\u6765\u9031\u706b\u66dc\u65e5\uff08\u3007\u6708\u3007\u65e5\uff09\u306b\u4e88\u5b9a\u3057\u3066\u304a\u308a\u307e\u3059\u6253\u3061\u5408\u308f\u305b\u306b\u3064\u304d\u307e\u3057\u3066\u3001\n\u4e0b\u8a18\u306e\u3068\u304a\u308a\u65e5\u7a0b\u3092\u5909\u66f4\u3055\u305b\u3066\u3044\u305f\u3060\u304d\u305f\u304f\u3001\u3054\u76f8\u8ac7\u7533\u3057\u4e0a\u3052\u307e\u3059\u3002\n\n\u25a0 \u5909\u66f4\u5185\u5bb9\n\u30fb\u5909\u66f4\u524d\uff1a\u3007\u6708\u3007\u65e5\uff08\u706b\uff09\u3007\u3007\u6642\u301c\u3007\u3007\u6642\n\u30fb\u5909\u66f4\u5f8c\uff1a\u3007\u6708\u3007\u65e5\uff08\u6c34\uff09\u3007\u3007\u6642\u301c\u3007\u3007\u6642\n\n\u5909\u66f4\u306e\u7406\u7531\u3068\u3044\u305f\u3057\u307e\u3057\u3066\u306f\u3001\u706b\u66dc\u65e5\u306e\u65e5\u7a0b\u304c\u4ed6\u793e\u3068\u306e\u91cd\u8981\u306a\u304a\u6253\u3061\u5408\u308f\u305b\u3068\u91cd\u8907\u3057\u3066\u3057\u307e\u3044\u3001\n\u672c\u4ef6\u306b\u5341\u5206\u306a\u3054\u6642\u9593\u3092\u5272\u304f\u3053\u3068\u304c\u3067\u304d\u306a\u3044\u72b6\u6cc1\u304c\u751f\u3058\u3066\u304a\u308a\u307e\u3059\u3002\n\u3064\u304d\u307e\u3057\u3066\u306f\u3001\u3088\u308a\u5186\u6ed1\u306b\u3054\u5bfe\u5fdc\u3044\u305f\u3060\u304f\u305f\u3081\u3001\u6c34\u66dc\u65e5\u306e\u65e5\u7a0b\u3078\u5909\u66f4\u3092\u304a\u9858\u3044\u7533\u3057\u4e0a\u3052\u307e\u3059\u3002\n\n\u306a\u304a\u3001\u6c34\u66dc\u65e5\u306e\u3007\u3007\u6642\u301c\u3007\u3007\u6642\u304c\u3054\u90fd\u5408\u306b\u5408\u308f\u306a\u3044\u5834\u5408\u306f\u3001\n\u3007\u3007\u6642\u301c\u3007\u3007\u6642\u3001\u307e\u305f\u306f\u3007\u3007\u65e5\uff08\u91d1\uff09\u3007\u3007\u6642\u301c\u3007\u3007\u6642\u306a\u3069\u3001\n\u4e0b\u8a18\u3088\u308a\u3054\u90fd\u5408\u306e\u3088\u3044\u6642\u9593\u5e2f\u3092\u3054\u6307\u5b9a\u3044\u305f\u3060\u3051\u307e\u3059\u3068\u5e78\u3044\u3067\u3059\u3002\n\n\u4f55\u5352\u3001\u3054\u591a\u5fd9\u306e\u6298\u3001\u304a\u624b\u6570\u3092\u304a\u304b\u3051\u3044\u305f\u3057\u307e\u3059\u304c\u3001\n\u4f55\u5352\u3088\u308d\u3057\u304f\u304a\u9858\u3044\u7533\u3057\u4e0a\u3052\u307e\u3059\u3002\n\n\u25a0 \u5909\u66f4\u5f8c\u306e\u65e5\u7a0b\u306e\u3054\u78ba\u8a8d\n\u3007\u3007\u682a\u5f0f\u4f1a\u793e \u3007\u3007 \u3007\u3007\n\uff08\u62c5\u5f53\u90e8\u7f72\u540d\uff09\nTEL\uff1a\u3007\u3007\u3007\u3007-\u3007\u3007\u3007\u3007\nE-MAIL\uff1a\u3007\u3007\u3007\u3007@\u3007\u3007\u3007\u3007.co.jp\n\n\u4ee5\u4e0a\n<\/code><\/pre>\n<p><strong>Word problem<\/strong><\/p>\n<blockquote>\n<p>\u308a\u3093\u3054\u304c1\u500b120\u5186\u3001\u307f\u304b\u3093\u304c1\u500b45\u5186\u3067\u3059\u3002\u308a\u3093\u3054\u30923\u500b\u3068\u307f\u304b\u3093\u30928\u500b\u8cb7\u3063\u3066\u30011,000\u5186\u672d\u3067\u6255\u3044\u307e\u3057\u305f\u3002\u304a\u3064\u308a\u306f\u3044\u304f\u3089\u3067\u3059\u304b\u3002\u8003\u3048\u65b9\u3082\u793a\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/blockquote>\n<p><em>(Apples cost 120 yen each and mandarins cost 45 yen each. You buy 3 apples and 8 mandarins and pay with a 1,000-yen bill. How much change do you get? Show your reasoning.)<\/em><\/p>\n<pre><code class=\"language-text\">\u308a\u3093\u30543\u500b\u3068\u307f\u304b\u30938\u500b\u306e\u5408\u8a08\u91d1\u984d\u3092\u8a08\u7b97\u3057\u307e\u3059\u3002\n\n- \u308a\u3093\u3054: 120\u5186 \u00d7 3\u500b = 360\u5186\n- \u307f\u304b\u3093: 45\u5186 \u00d7 8\u500b = 360\u5186\n- \u5408\u8a08: 360\u5186 + 360\u5186 = 720\u5186\n\n1,000\u5186\u672d\u3067\u6255\u3063\u305f\u306e\u3067\u3001\u304a\u3064\u308a\u306f:\n\n1,000\u5186 - 720\u5186 = 280\u5186\n\n**\u304a\u3064\u308a\u306f280\u5186\u3067\u3059\u3002**\n<\/code><\/pre>\n<p>Reference: The correct answer is 280 yen (120\u00d73 = 360, 45\u00d78 = 360, 1,000 \u2212 720 = 280).<\/p>\n<p><strong>Knowledge<\/strong><\/p>\n<blockquote>\n<p>\u65e5\u672c\u306e\u90fd\u9053\u5e9c\u770c\u306e\u3046\u3061\u3001\u6d77\u306b\u9762\u3057\u3066\u3044\u306a\u3044\u770c\u3092\u3059\u3079\u3066\u6319\u3052\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/blockquote>\n<p><em>(List all of Japan&#8217;s prefectures that do not border the sea.)<\/em><\/p>\n<pre><code class=\"language-text\">\u65e5\u672c\u306e\u90fd\u9053\u5e9c\u770c\u3067\u3001\u6d77\u306b\u9762\u3057\u3066\u3044\u306a\u3044\uff08\u5185\u9678\uff09\u306e12\u770c\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3067\u3059\u3002\n\n1. \u5317\u6d77\u9053\n2. \u9752\u68ee\u770c\n3. \u5ca9\u624b\u770c\n4. \u5bae\u57ce\u770c\n5. \u79cb\u7530\u770c\n6. \u5c71\u5f62\u770c\n7. \u798f\u5cf6\u770c\n8. \u8328\u57ce\u770c\n9. \u6803\u6728\u770c\n10. \u7fa4\u99ac\u770c\n11. \u57fc\u7389\u770c\n12. \u5343\u8449\u770c\n13. \u6771\u4eac\u90fd\n14. \u795e\u5948\u5ddd\u770c\n\n\u5408\u8a0814\u770c\u3067\u3059\u3002\n<\/code><\/pre>\n<p>Reference: The correct answer is eight prefectures: Tochigi, Gunma, Saitama, Yamanashi, Nagano, Gifu, Shiga and Nara.<\/p>\n<p><strong>Constrained writing<\/strong><\/p>\n<blockquote>\n<p>\u300c\u6625\u300d\u3092\u30c6\u30fc\u30de\u306b\u3057\u305f\u4ff3\u53e5\u30923\u3064\u3001\u4e94\u30fb\u4e03\u30fb\u4e94\u306e\u97f3\u6570\u3092\u5b88\u3063\u3066\u4f5c\u3063\u3066\u304f\u3060\u3055\u3044\u3002\u305d\u308c\u305e\u308c\u306b\u4e00\u8a00\u306e\u8aac\u660e\u3092\u4ed8\u3051\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/blockquote>\n<p><em>(Write three haiku on the theme of spring, keeping the 5-7-5 syllable pattern, each with a one-line explanation.)<\/em><\/p>\n<pre><code class=\"language-text\">\u6625\u3092\u30c6\u30fc\u30de\u306b\u3057\u305f\u4ff3\u53e5\u30923\u3064\u3001\u4e94\u30fb\u4e03\u30fb\u4e94\u306e\u97f3\u6570\u3092\u5b88\u3063\u3066\u4f5c\u308a\u307e\u3057\u305f\u3002\n\n**\u2460 \u82bd\u5439\u304f\u8349\u306b \u98a8\u304c\u3075\u308f\u308a\u3068 \u6625\u306e\u4fbf\u308a**\n\uff08\u3081\u3076\u304f\u304f\u3055\u306b\u304b\u305c\u304c\u3075\u308f\u308a\u3068 \u306f\u308b\u306e\u306f\u304c\u304d\uff09\n**\u8aac\u660e\uff1a** \u5730\u9762\u306b\u305d\u3063\u3068\u82bd\u3092\u51fa\u3057\u305f\u8349\u306b\u3001\u3084\u308f\u3089\u304b\u306a\u98a8\u304c\u5439\u304d\u3001\u6625\u306e\u8a2a\u308c\u3092\u904b\u3093\u3067\u304f\u308b\u60c5\u666f\u3002\u9759\u304b\u306a\u6625\u306e\u59cb\u307e\u308a\u3092\u3001\u98a8\u3068\u8349\u306e\u3075\u308c\u3042\u3044\u3067\u8868\u73fe\u3057\u3066\u3044\u307e\u3059\u3002\n\n**\u2461 \u685c\u306e\u679d\u306b \u96ea\u304c\u3068\u3051 \u6625\u306e\u4fbf\u308a**\n\uff08\u3055\u304f\u3089\u306e\u3048\u3060\u306b\u3086\u304d\u304c\u3068\u3051 \u306f\u308b\u306e\u306f\u304c\u304d\uff09\n**\u8aac\u660e\uff1a** \u685c\u306e\u679d\u306b\u6b8b\u3063\u305f\u96ea\u304c\u6eb6\u3051\u3001\u6625\u306e\u8a2a\u308c\u3092\u544a\u3052\u308b\u60c5\u666f\u3002\u51ac\u306e\u6b8b\u308a\u3068\u6625\u306e\u8a2a\u308c\u304c\u540c\u3058\u679d\u306b\u91cd\u306a\u308b\u3001\u79fb\u308d\u3044\u306e\u7f8e\u3057\u3044\u77ac\u9593\u3092\u6349\u3048\u3066\u3044\u307e\u3059\u3002\n\n**\u2462 \u82b1\u898b\u306e\u5e2d\u306b \u6625\u306e\u4fbf\u308a \u82b1\u3073\u3089\u821e\u3046**\n\uff08\u306f\u306a\u307f\u306e\u3056\u304d\u306b \u306f\u308b\u306e\u306f\u304c\u304d \u306f\u306a\u3073\u3089\u307e\u3046\uff09\n**\u8aac\u660e\uff1a** \u82b1\u898b\u306e\u5e2d\u3067\u6625\u306e\u4fbf\u308a\u3092\u8fce\u3048\u308b\u3001\u8cd1\u3084\u304b\u3067\u660e\u308b\u3044\u60c5\u666f\u3002\u82b1\u3073\u3089\u304c\u821e\u3044\u6563\u308b\u6625\u306e\u5bb4\u3092\u3001\u4eba\u3005\u306e\u96c6\u3046\u5834\u3068\u3057\u3066\u63cf\u3044\u3066\u3044\u307e\u3059\u3002\n\n\u3044\u305a\u308c\u3082\u300c\u6625\u306e\u4fbf\u308a\u300d\u3068\u3044\u3046\u8a00\u8449\u3067\u6625\u306e\u8a2a\u308c\u3092\u8c61\u5fb4\u7684\u306b\u8868\u73fe\u3057\u3066\u3044\u307e\u3059\u3002\u3054\u5e0c\u671b\u304c\u3042\u308c\u3070\u3001\u5225\u306e\u60c5\u666f\u3084\u5b63\u7bc0\u306e\u79fb\u308d\u3044\u3092\u30c6\u30fc\u30de\u306b\u3057\u305f\u4ff3\u53e5\u3082\u4f5c\u6210\u3067\u304d\u307e\u3059\u3002\n<\/code><\/pre>\n<h3>Answers About Images (Verbatim)<\/h3>\n<p>Under the same conditions, we gave the model images we drew ourselves with code (a chart and a table in Japanese) and asked about them. Answers are unedited; the correct answers were computed by the code that drew the images.<\/p>\n<p><strong>Reading a chart<\/strong><\/p>\n<p><img decoding=\"async\" alt=\"Reading a chart\" src=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/wp-content\/uploads\/2026\/09\/lmw-lab-vision-chart-v1.png\" \/><\/p>\n<blockquote>\n<p>\u3053\u306e\u30b0\u30e9\u30d5\u3067\u6765\u5ba2\u6570\u304c\u6700\u3082\u591a\u3044\u66dc\u65e5\u3068\u3001\u305d\u306e\u4eba\u6570\u3092\u7b54\u3048\u3066\u304f\u3060\u3055\u3044\u3002\u307e\u305f\u3001\u5e73\u65e5(\u6708\u66dc\u65e5\u301c\u91d1\u66dc\u65e5)\u306e\u6765\u5ba2\u6570\u306e\u5408\u8a08\u3082\u6c42\u3081\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/blockquote>\n<p><em>(Which day has the most visitors in this chart, and how many? Also give the weekday (Mon-Fri) total.)<\/em><\/p>\n<pre><code class=\"language-text\">\u3053\u306e\u30b0\u30e9\u30d5\u304b\u3089\u8aad\u307f\u53d6\u308c\u308b\u60c5\u5831\u3092\u6574\u7406\u3057\u307e\u3059\u3002\n\n**\u6765\u5ba2\u6570\u304c\u6700\u3082\u591a\u3044\u66dc\u65e5**\n- **\u571f\u66dc\u65e5**\uff1a**260\u4eba**\n\n**\u5e73\u65e5\uff08\u6708\u66dc\u65e5\u301c\u91d1\u66dc\u65e5\uff09\u306e\u6765\u5ba2\u6570\u306e\u5408\u8a08**\n- \u6708\u66dc\u65e5\uff1a120\u4eba\n- \u706b\u66dc\u65e5\uff1a95\u4eba\n- \u6c34\u66dc\u65e5\uff1a110\u4eba\n- \u6728\u66dc\u65e5\uff1a130\u4eba\n- \u91d1\u66dc\u65e5\uff1a180\u4eba\n\n120 + 95 + 110 + 130 + 180 = **635\u4eba**\n\n\u3057\u305f\u304c\u3063\u3066\u3001\u7b54\u3048\u306f\u300c**\u571f\u66dc\u65e5\uff08260\u4eba\uff09**\u300d\u3067\u3001\u5e73\u65e5\u306e\u5408\u8a08\u306f**635\u4eba**\u3067\u3059\u3002\n<\/code><\/pre>\n<p>Reference: Correct answer: Sat with 260 visitors; the weekday total is 635.<\/p>\n<p><strong>Reading a table and calculating<\/strong><\/p>\n<p><img decoding=\"async\" alt=\"Reading a table and calculating\" src=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/wp-content\/uploads\/2026\/09\/lmw-lab-vision-receipt-v1.png\" \/><\/p>\n<blockquote>\n<p>\u3053\u306e\u8868\u306e\u54c1\u76ee\u3054\u3068\u306e\u91d1\u984d(\u6570\u91cf\u00d7\u5358\u4fa1)\u3068\u3001\u5408\u8a08\u91d1\u984d\u3092\u7b54\u3048\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/blockquote>\n<p><em>(Give the amount for each item (quantity \u00d7 unit price) in this table, and the total.)<\/em><\/p>\n<pre><code class=\"language-text\">\u3053\u306e\u8868\u306e\u8a08\u7b97\u7d50\u679c\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3067\u3059\u3002\n\n| \u54c1\u76ee | \u6570\u91cf | \u5358\u4fa1 | \u91d1\u984d\uff08\u6570\u91cf\u00d7\u5358\u4fa1\uff09 |\n|---|---:|---:|---:|\n| \u308a\u3093\u3054 | 3 | 120\u5186 | **360\u5186** |\n| \u307f\u304b\u3093 | 8 | 45\u5186 | **360\u5186** |\n| \u725b\u4e73 | 2 | 198\u5186 | **396\u5186** |\n| \u98df\u30d1\u30f3 | 1 | 238\u5186 | **238\u5186** |\n\n**\u5408\u8a08\u91d1\u984d\uff1a1,354\u5186**\n\n\u8a08\u7b97\u306e\u904e\u7a0b\uff1a\n- \u308a\u3093\u3054\uff1a3 \u00d7 120\u5186 = 360\u5186\n- \u307f\u304b\u3093\uff1a8 \u00d7 45\u5186 = 360\u5186\n- \u725b\u4e73\uff1a2 \u00d7 198\u5186 = 396\u5186\n- \u98df\u30d1\u30f3\uff1a1 \u00d7 238\u5186 = 238\u5186\n\n360 + 360 + 396 + 238 = 1,354\u5186\n<\/code><\/pre>\n<p>Reference: Correct answer: 360 yen, 360 yen, 396 yen, 238 yen; total 1,354 yen.<\/p>\n<p><!-- \/lmw:lab --><\/p>\n<h2>How to Get It<\/h2>\n<p>This model is released in GGUF format and can be downloaded from the <code>ggml-org<\/code> repository. The adoption of the GGUF format enables operations that flexibly combine CPU inference and GPU offloading, allowing the 9.4B parameter model to run efficiently even in local environments with limited memory resources.<\/p>\n<p>Tools from the <code>llama.cpp<\/code> ecosystem are recommended for acquisition and execution. For example, when using <code>llama.app<\/code>, you can load the model directly from Hugging Face and launch an API server with the following command:<\/p>\n<pre><code class=\"language-bash\">llama serve -hf ggml-org\/MiMo-V2.6-Distill-Qwen-9B-GGUF\n<\/code><\/pre>\n<p>Since this model is multimodal, an <code>mmproj<\/code> file for the vision encoder is required in addition to the main model file for text. The repository includes a <code>Q8_0<\/code> quantized <code>mmproj<\/code> file, which should be specified and loaded when using image inputs. Even in the quantized version, efforts are made to maintain visual information recognition accuracy by allocating a high-precision bit count of Q8_0 to the vision encoder.<\/p>\n<p>Additionally, based on the specifications of the original model, it is recommended to use the MiMo v2.6 exclusive chat template during inference. When using engines such as SGLang, passing the <code>--reasoning-parser mimo<\/code> flag allows you to properly parse and utilize the aforementioned thinking process. It is a very easy-to-handle package for engineers looking to build a &#8220;thinking agent&#8221; in a local environment.<\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/02\/clef-flash-specs-performance-and-use-cases\/\">clef-flash Vision-Language Model: Our Test Answers, 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/28\/apple-lensvlm-9b-2\/\">LensVLM-9B Vision-Language Model: 4GB+ VRAM, GGUF Builds<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/04\/glm-5-3-flash-gguf-released\/\">GLM-5.3-Flash-GGUF Vision-Language Model: ~150GB Memory<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/02\/ggml-org-openjev-gguf-released-2\/\">OpenJev-GGUF 27.4B Decision-Making Specialized Model: 24GB+ VRAM<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Find models by VRAM<\/strong> (This model runs from the 12GB tier) \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-12gb-en\/\">Other models that run on a 12GB GPU<\/a><\/li>\n<li><strong>Explore the same model family<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-xiaomimimo-mimo-v2-6-en\/\">MiMo-V2.6 family overview (4 articles, 4 converted builds)<\/a><\/li>\n<li><strong>Engines that run this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-llama-cpp-en\/\">llama.cpp<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-ollama-en\/\">Ollama<\/a><\/li>\n<li><strong>What Q8_0 mean and where to get this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF format guide and models<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">Quantization and model-format glossary<\/a><\/li>\n<li><strong>Learn about the publisher<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-alibaba-en\/\">Alibaba (Qwen): models, licenses and articles<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/ggml-org\/MiMo-V2.6-Distill-Qwen-9B-GGUF\">https:\/\/huggingface.co\/ggml-org\/MiMo-V2.6-Distill-Qwen-9B-GGUF<\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/XiaomiMiMo\/MiMo-V2.6-Distill-Qwen-9B\">https:\/\/huggingface.co\/XiaomiMiMo\/MiMo-V2.6-Distill-Qwen-9B<\/a><\/li>\n<\/ul>\n<p><!-- lmw:updates --><\/p>\n<h2>Update History<\/h2>\n<ul>\n<li>2026-09-24: Rebuilt the article: Added a &#8220;can you run it locally?&#8221; verdict from the distribution formats, converted builds, engine registries, license terms and measured compression<\/li>\n<li>2026-09-25: Changed the title to show what the article covers (VRAM requirements, file list, etc.).<\/li>\n<li>2026-09-28: Added our own measurements: Japanese token efficiency.<\/li>\n<li>2026-09-30: Added our own measurements: CPU speed and answers to Japanese questions.<\/li>\n<li>2026-09-30: Changed the title to show what the article covers (VRAM requirements, file list, etc.).<\/li>\n<li>2026-10-06: Added our own measurements: what is inside the GGUF file.<\/li>\n<\/ul>\n<p><!-- \/lmw:updates --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Download the GGUF version of MiMo-V2.6-Distill-Qwen-9B, a 9.4B agentic model for coding and cybersecurity.<\/p>\n","protected":false},"author":1,"featured_media":7829,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[310],"tags":[161,163,1950,165,520,996,1547,1952,1954],"class_list":["post-2416","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-models","tag-ggml-en","tag-gguf-en","tag-mimo-v2-6-distill-qwen-9b-en","tag-moe-en","tag-qwen-en","tag-qwen3-5-en","tag-verified","tag-vlm-en","tag-xiaomi-en"],"lang":"en","translations":{"en":2416,"ja":2414},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/2416","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=2416"}],"version-history":[{"count":32,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/2416\/revisions"}],"predecessor-version":[{"id":15613,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/2416\/revisions\/15613"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/7829"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=2416"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=2416"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=2416"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}