{"id":19470,"date":"2026-11-19T01:10:51","date_gmt":"2026-11-18T16:10:51","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/11\/19\/lfm3-1-7b-gguf-release\/"},"modified":"2026-11-19T07:21:28","modified_gmt":"2026-11-18T22:21:28","slug":"lfm3-1-7b-gguf-release","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/19\/lfm3-1-7b-gguf-release\/","title":{"rendered":"LFM3-1.7B-GGUF Text Generation Model: Our Test Answers, 4GB+ 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\/LFM3-1.7B-GGUF\">ggml-org\/LFM3-1.7B-GGUF<\/a><\/td>\n<\/tr>\n<tr>\n<td>Family guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-liquidai-lfm3-en\/\">LFM3 guide (2 articles)<\/a><\/td>\n<\/tr>\n<tr>\n<td>Publisher guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-liquidai-en\/\">Liquid AI: models and licenses<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-11-19<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>lfm1.0<\/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>LFM3-1.7B-Q4_K_M.gguf<\/code> (Q4_K_M) on our CPU-only server (Neoverse-N1, 3 threads, llama.cpp b12418): generation at 4.4 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 7% fewer tokens than the Qwen3 tokenizer for the same Japanese text, so about 1.07\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>ggml-org has released a GGUF quantized repository for the &#8220;LiquidAI\/LFM3-1.7B&#8221; text generation model, developed by LiquidAI, titled &#8220;<a href=\"https:\/\/huggingface.co\/ggml-org\/LFM3-1.7B-GGUF\">ggml-org\/LFM3-1.7B-GGUF<\/a>&#8220;. The models were converted using an automated script and include formats such as Q8_0 and Q4_K_M, adopting the same quantization settings as those provided by LiquidAI officially.<\/p>\n<p>The base model, &#8220;<a href=\"https:\/\/huggingface.co\/LiquidAI\/LFM3-1.7B\">LiquidAI\/LFM3-1.7B<\/a>&#8220;, is a 1.7B parameter text generation model designed for local agentic functions and specialized applications. It employs a unique tri-hybrid architecture and supports a long-context window of up to 256K tokens.<\/p>\n<p>Note that running the GGUF models from this repository requires a build of <code>llama.cpp<\/code> that supports LFM3.<\/p>\n<h2>Specifications<\/h2>\n<p>The specifications listed on the model card for the base &#8220;LiquidAI\/LFM3-1.7B&#8221; model are as follows:<\/p>\n<ul>\n<li>Parameter count: 1.73B<\/li>\n<li>Architecture: 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention<\/li>\n<li>Context length: 256K tokens (input + output)<\/li>\n<\/ul>\n<h2>Performance<\/h2>\n<p>The following are the benchmark results reported on the model card for the base &#8220;LiquidAI\/LFM3-1.7B&#8221; model. These are actual measurements taken by the publisher using vLLM on the unquantized model.<\/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>Benchmark<\/th>\n<th>LFM3 1.7B<\/th>\n<th>LFM2.5 2.6B<\/th>\n<th>MiniCPM5 2B<\/th>\n<th>Gemma 4 E4B<\/th>\n<th>Qwen3.5 4B<\/th>\n<th>Qwen3.5 9B<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><strong>Agents<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>LiveClaw<\/td>\n<td>45.60<\/td>\n<td>14.70<\/td>\n<td>30.37<\/td>\n<td>20.36<\/td>\n<td>19.94<\/td>\n<td>35.77<\/td>\n<\/tr>\n<tr>\n<td>Claw-Eval General (EN), average<\/td>\n<td>68.64<\/td>\n<td>62.63<\/td>\n<td>60.74<\/td>\n<td>56.14<\/td>\n<td>61.96<\/td>\n<td>66.53<\/td>\n<\/tr>\n<tr>\n<td>Claw-Eval General (EN), pass^3<\/td>\n<td>51.40<\/td>\n<td>37.52<\/td>\n<td>34.58<\/td>\n<td>22.43<\/td>\n<td>42.99<\/td>\n<td>51.87<\/td>\n<\/tr>\n<tr>\n<td>BrowseComp-Plus (OpenClaw subset)<\/td>\n<td>37.00<\/td>\n<td>26.33<\/td>\n<td>16.83<\/td>\n<td>21.00<\/td>\n<td>24.67<\/td>\n<td>38.00<\/td>\n<\/tr>\n<tr>\n<td>WebArena-Verified<\/td>\n<td>38.42<\/td>\n<td>3.02<\/td>\n<td>9.11<\/td>\n<td>17.06<\/td>\n<td>21.92<\/td>\n<td>28.94<\/td>\n<\/tr>\n<tr>\n<td>EnterpriseOps-Gym<\/td>\n<td>28.20<\/td>\n<td>7.94<\/td>\n<td>13.41<\/td>\n<td>9.86<\/td>\n<td>25.96<\/td>\n<td>28.97<\/td>\n<\/tr>\n<tr>\n<td>AutomationBench (public)<\/td>\n<td>41.29<\/td>\n<td>0.94<\/td>\n<td>4.71<\/td>\n<td>1.92<\/td>\n<td>8.67<\/td>\n<td>15.10<\/td>\n<\/tr>\n<tr>\n<td><strong>Tool use<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>BFCL V4<\/td>\n<td>71.39<\/td>\n<td>55.89<\/td>\n<td>62.65<\/td>\n<td>48.25<\/td>\n<td>55.12<\/td>\n<td>62.83<\/td>\n<\/tr>\n<tr>\n<td>ToolSandbox<\/td>\n<td>80.36<\/td>\n<td>78.04<\/td>\n<td>68.16<\/td>\n<td>69.27<\/td>\n<td>75.40<\/td>\n<td>76.41<\/td>\n<\/tr>\n<tr>\n<td>MCP-Atlas<\/td>\n<td>32.57<\/td>\n<td>16.45<\/td>\n<td>26.38<\/td>\n<td>6.19<\/td>\n<td>41.37<\/td>\n<td>42.67<\/td>\n<\/tr>\n<tr>\n<td>\u03c4\u00b3-bench (4 domains), average<\/td>\n<td>68.01<\/td>\n<td>56.77<\/td>\n<td>69.44<\/td>\n<td>33.53<\/td>\n<td>65.98<\/td>\n<td>67.11<\/td>\n<\/tr>\n<tr>\n<td><strong>Agentic coding<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>SWE-bench Verified (OpenCode)<\/td>\n<td>43.40<\/td>\n<td>18.00<\/td>\n<td>34.80<\/td>\n<td>0.50<\/td>\n<td>41.20<\/td>\n<td>51.20<\/td>\n<\/tr>\n<tr>\n<td>SWE-bench Multilingual (OpenCode)<\/td>\n<td>23.00<\/td>\n<td>8.00<\/td>\n<td>15.67<\/td>\n<td>0.67<\/td>\n<td>23.33<\/td>\n<td>35.00<\/td>\n<\/tr>\n<tr>\n<td>Terminal-Bench 2.1 (OpenCode)<\/td>\n<td>12.92<\/td>\n<td>0.00<\/td>\n<td>5.62<\/td>\n<td>0.00<\/td>\n<td>13.48<\/td>\n<td>17.98<\/td>\n<\/tr>\n<tr>\n<td><strong>Coding<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>LiveCodeBench v6<\/td>\n<td>73.46<\/td>\n<td>60.57<\/td>\n<td>70.52<\/td>\n<td>71.00<\/td>\n<td>61.99<\/td>\n<td>69.86<\/td>\n<\/tr>\n<tr>\n<td>LiveCodeBench Pro 25Q2<\/td>\n<td>31.74<\/td>\n<td>19.16<\/td>\n<td>29.34<\/td>\n<td>29.94<\/td>\n<td>24.25<\/td>\n<td>34.43<\/td>\n<\/tr>\n<tr>\n<td>SciCode<\/td>\n<td>28.47<\/td>\n<td>16.32<\/td>\n<td>27.78<\/td>\n<td>25.00<\/td>\n<td>23.02<\/td>\n<td>31.60<\/td>\n<\/tr>\n<tr>\n<td><strong>Instruction following<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>IFEval<\/td>\n<td>96.66<\/td>\n<td>95.39<\/td>\n<td>87.83<\/td>\n<td>90.02<\/td>\n<td>92.52<\/td>\n<td>92.08<\/td>\n<\/tr>\n<tr>\n<td>IFBench<\/td>\n<td>73.03<\/td>\n<td>60.48<\/td>\n<td>62.08<\/td>\n<td>44.56<\/td>\n<td>38.16<\/td>\n<td>48.84<\/td>\n<\/tr>\n<tr>\n<td>IFStruct<\/td>\n<td>93.72<\/td>\n<td>82.18<\/td>\n<td>72.65<\/td>\n<td>78.45<\/td>\n<td>87.05<\/td>\n<td>89.20<\/td>\n<\/tr>\n<tr>\n<td>Multi-IF<\/td>\n<td>89.10<\/td>\n<td>84.80<\/td>\n<td>73.19<\/td>\n<td>81.03<\/td>\n<td>80.32<\/td>\n<td>84.44<\/td>\n<\/tr>\n<tr>\n<td><strong>Knowledge<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>GPQA Diamond<\/td>\n<td>63.37<\/td>\n<td>57.78<\/td>\n<td>65.15<\/td>\n<td>57.88<\/td>\n<td>75.76<\/td>\n<td>80.40<\/td>\n<\/tr>\n<tr>\n<td>Humanity&#8217;s Last Exam (no tools)<\/td>\n<td>7.17<\/td>\n<td>5.88<\/td>\n<td>8.20<\/td>\n<td>4.77<\/td>\n<td>12.84<\/td>\n<td>16.41<\/td>\n<\/tr>\n<tr>\n<td>Humanity&#8217;s Last Exam (with tools)<\/td>\n<td>13.90<\/td>\n<td>9.60<\/td>\n<td>11.50<\/td>\n<td>6.00<\/td>\n<td>11.60<\/td>\n<td>17.50<\/td>\n<\/tr>\n<tr>\n<td>AA-Omniscience (public)<\/td>\n<td>0.50<\/td>\n<td>-33.17<\/td>\n<td>-5.00<\/td>\n<td>-15.33<\/td>\n<td>-57.17<\/td>\n<td>-28.00<\/td>\n<\/tr>\n<tr>\n<td>AA-Omniscience accuracy (public)<\/td>\n<td>7.07<\/td>\n<td>8.75<\/td>\n<td>9.13<\/td>\n<td>9.83<\/td>\n<td>15.67<\/td>\n<td>13.17<\/td>\n<\/tr>\n<tr>\n<td>AA-Omniscience non-hallucination (public)<\/td>\n<td>92.93<\/td>\n<td>53.69<\/td>\n<td>84.44<\/td>\n<td>72.09<\/td>\n<td>13.64<\/td>\n<td>52.59<\/td>\n<\/tr>\n<tr>\n<td><strong>Long context<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>AA-LCR<\/td>\n<td>52.83<\/td>\n<td>6.00<\/td>\n<td>49.34<\/td>\n<td>39.33<\/td>\n<td>52.67<\/td>\n<td>62.00<\/td>\n<\/tr>\n<tr>\n<td>RULER 128K<\/td>\n<td>65.56<\/td>\n<td>1.15<\/td>\n<td>37.96<\/td>\n<td>18.82<\/td>\n<td>84.63<\/td>\n<td>87.11<\/td>\n<\/tr>\n<tr>\n<td>Average<\/td>\n<td>49.37<\/td>\n<td>31.55<\/td>\n<td>39.19<\/td>\n<td>31.74<\/td>\n<td>39.27<\/td>\n<td>47.24<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>According to the figures provided by the publisher, LFM3 1.7B shows a strong tendency toward tool use and agentic tasks despite being a small model. It recorded 71.39 in BFCL V4, which measures the accuracy of function selection and argument construction, the highest score among the compared models. It also scored 43.40 in SWE-bench Verified (OpenCode), which measures the ability to resolve actual GitHub issues, outperforming Qwen3.5 4B (41.20). It also demonstrated a high score of 96.66 in IFEval, which measures adherence to formal instructions.<\/p>\n<p>On the other hand, it falls behind larger models in benchmarks requiring specialized knowledge. It scored 63.37 in GPQA Diamond, which measures PhD-level difficult questions, trailing models such as Qwen3.5 4B (75.76) and Qwen3.5 9B (80.40). In RULER 128K, which measures whether the nominal context length can actually be handled, it remained at 65.56, showing a gap compared to the Qwen3.5 series (over 80%).<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>The base model &#8220;LiquidAI\/LFM3-1.7B&#8221; is specifically designed for local agentic functions, tool calling, structured data extraction, and fine-tuning for specific domains.<\/p>\n<p>According to the model card, it has undergone post-training for various agent construction harnesses such as Hermes Agent, Pi, and OpenClaw. By leveraging the 256K token context window, it can efficiently process deferred tools and function calls using XML format. It supports configurations for dynamically searching and loading tool definitions within prompts, making it suitable for implementing agent applications that handle numerous tools. It also features built-in support for outputting reasoning traces (thinking) by default.<\/p>\n<p>Supported languages include Japanese, English, Arabic, Chinese, French, German, Italian, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, and Polish.<\/p>\n<p>However, because it is a compact 1.7B parameter model, the model card explicitly states that it is not recommended for complex multi-step reasoning. When executing knowledge-intensive tasks, it is recommended to combine it with search or RAG (Retrieval-Augmented Generation).<\/p>\n<p>The models provided in this repository are GGUF conversions of the base model, intended to allow users to utilize the agentic and tool-use capabilities of the base model on local PC environments.<\/p>\n<h2>How It Differs from Similar Models<\/h2>\n<p>Previously, our site covered another format of the same base model: &#8220;<a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/11\/17\/lfm3-17b-mlx-5bit\/\">LFM3-1.7B-MLX-5bit: Long-context agentic text generation model: Requires 4GB+ VRAM<\/a>&#8220;.<\/p>\n<p>The main difference between that and the newly released &#8220;ggml-org\/LFM3-1.7B-GGUF&#8221; lies in the distribution format and the intended execution environment. The previously introduced repository was a 5-bit quantized version (MLX format) for the MLX framework, specialized for use in Apple Silicon environments. In contrast, this model is distributed in the general-purpose GGUF format, offering multiple quantization precisions such as Q8_0 and Q4_K_M. This allows for flexible execution not only on Mac but also on Linux and Windows environments, as well as various CPUs and GPUs via <code>llama.cpp<\/code> or compatible engines.<\/p>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 1.7B parameters (taken from the base model LiquidAI\/LFM3-1.7B)<\/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>4GB (laptop iGPU \/ phone class)<\/td>\n<td>BF16<\/td>\n<td>3.2GB<\/td>\n<td>3.9GB<\/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>lfm1.0<\/code> (Commercial use allowed with conditions):<\/strong> LiquidAI&#8217;s LFM Open License v1.0. Commercial use is allowed, except by legal entities with annual revenue of $10 million or more (Section 5). Redistribution requires the license text and notice of changes.<\/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>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>642<\/strong><\/td>\n<td><strong>1.15\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 7% fewer tokens than the Qwen3 tokenizer for the same Japanese text, so about 1.07\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\/LiquidAI\/LFM3-1.7B\">LiquidAI\/LFM3-1.7B<\/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\/LFM3-1.7B-GGUF\/blob\/main\/LFM3-1.7B-Q4_K_M.gguf\">LFM3-1.7B-Q4_K_M.gguf<\/a> (1.02GB, <code>Q4_K_M<\/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>lfm3<\/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>24<\/td>\n<\/tr>\n<tr>\n<td>Vocabulary size<\/td>\n<td>128,000<\/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>Q4_K 73.6% \/ Q6_K 26.4% \/ F32 0.0%<\/td>\n<\/tr>\n<tr>\n<td>Average bits per weight<\/td>\n<td>5.05 bits<\/td>\n<\/tr>\n<tr>\n<td>Embedding \/ output layer type<\/td>\n<td>Q6_K \/ shared with the embedding<\/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>32.8 tokens\/s<\/td>\n<\/tr>\n<tr>\n<td>Generation (128 tokens)<\/td>\n<td>4.4 tokens\/s<\/td>\n<\/tr>\n<tr>\n<td>Generation in Japanese characters<\/td>\n<td>about 6.9 characters\/s<\/td>\n<\/tr>\n<tr>\n<td>Peak memory (context 4,096 tokens)<\/td>\n<td>2.3GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>Conditions: Neoverse-N1, 3 threads, no GPU, llama.cpp b12418, <code>Q4_K_M<\/code> (1.02GB) from <a href=\"https:\/\/huggingface.co\/ggml-org\/LFM3-1.7B-GGUF\">ggml-org\/LFM3-1.7B-GGUF<\/a>, measured 2026-11-19 (JST). 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\/11\/17\/liquidai-lfm3-omni-2b-mlx-4bit-apple-silicon\/\">LFM3-Omni-2B<\/a><\/td>\n<td><code>Q4_K_M<\/code><\/td>\n<td>1.02GB<\/td>\n<td>18.1 tokens\/s<\/td>\n<td>28.1 chars\/s<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/jais-3-0-9b-gguf-released\/\">Jais-3-0.9B<\/a><\/td>\n<td><code>Q4_K_M<\/code><\/td>\n<td>0.62GB<\/td>\n<td>4.8 tokens\/s<\/td>\n<td>6.2 chars\/s<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/08\/minicpm5-2b-released\/\">MiniCPM5-2B<\/a><\/td>\n<td><code>Q4_K_M<\/code><\/td>\n<td>1.45GB<\/td>\n<td>13.9 tokens\/s<\/td>\n<td>20.9 chars\/s<\/td>\n<\/tr>\n<tr>\n<td>Qwen3-4B<\/td>\n<td><code>Q4_K_M<\/code><\/td>\n<td>2.33GB<\/td>\n<td>6.8 tokens\/s<\/td>\n<td>\u2014<\/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<h4>Commands We Ran<\/h4>\n<p>We used the official llama.cpp build <code>llama-b12418-bin-ubuntu-arm64.tar.gz<\/code> from <a href=\"https:\/\/github.com\/ggml-org\/llama.cpp\/releases\">the releases page<\/a> and downloaded these files:<\/p>\n<pre><code class=\"language-text\">https:\/\/huggingface.co\/ggml-org\/LFM3-1.7B-GGUF\/resolve\/main\/LFM3-1.7B-Q4_K_M.gguf\n<\/code><\/pre>\n<p>Speed (llama-bench):<\/p>\n<pre><code class=\"language-bash\">nice -n 10 .\/llama-bench -m LFM3-1.7B-Q4_K_M.gguf -t 3 -p 512 -n 128 -r 2 -o json\n<\/code><\/pre>\n<p>Answers: we started llama-server like this (we pick a free port each time; shown as 8080) and sent each question to <code>\/v1\/chat\/completions<\/code> with the body below (only the question text changes; this example is the business-email question):<\/p>\n<pre><code class=\"language-bash\">nice -n 10 .\/llama-server -m LFM3-1.7B-Q4_K_M.gguf -t 3 -c 4096 --jinja --host 127.0.0.1 --port 8080 --no-mmproj\n<\/code><\/pre>\n<pre><code class=\"language-bash\">curl -s http:\/\/127.0.0.1:8080\/v1\/chat\/completions \\\n  -H 'Content-Type: application\/json' \\\n  -d @- &lt;&lt;'EOF'\n{\n  &quot;messages&quot;: [\n    {\n      &quot;role&quot;: &quot;user&quot;,\n      &quot;content&quot;: &quot;\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&quot;\n    }\n  ],\n  &quot;temperature&quot;: 0,\n  &quot;seed&quot;: 0,\n  &quot;max_tokens&quot;: 1024,\n  &quot;chat_template_kwargs&quot;: {\n    &quot;enable_thinking&quot;: false\n  }\n}\nEOF\n<\/code><\/pre>\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\u304c\u7d041\u5e74\u534a\u304b\u3051\u3066\u6539\u4fee\u3057\u3001\u518d\u958b\u9928\u3057\u307e\u3057\u305f\u3002\u5ea7\u5e2d\u6570\u3092\u5897\u3084\u3057\u3066\u5b66\u7fd2\u74b0\u5883\u3092\u6539\u5584\u3057\u3001\u8535\u66f8\u306e\u898b\u76f4\u3057\u3084\u5efa\u7269\u66f4\u65b0\u3082\u9032\u3081\u3001\u5229\u7528\u8005\u304b\u3089\u306e\u597d\u610f\u7684\u306a\u53cd\u5fdc\u304c\u5f97\u3089\u308c\u3066\u3044\u307e\u3059\u3002\u4e00\u65b9\u3067\u99d0\u8eca\u5834\u4e0d\u8db3\u3084\u8077\u54e1\u8ca0\u62c5\u306a\u3069\u306e\u8ab2\u984c\u306f\u6b8b\u3063\u3066\u304a\u308a\u3001\u4eca\u5f8c\u306e\u5bfe\u7b56\u304c\u6c42\u3081\u3089\u308c\u3066\u3044\u307e\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\u6253\u3061\u5408\u308f\u305b\u65e5\u7a0b\u306e\u5909\u66f4\u306b\u3064\u3044\u3066\n\n[\u76f8\u624b\u306e\u540d\u524d] \u69d8\n\n\u3044\u3064\u3082\u304a\u4e16\u8a71\u306b\u306a\u3063\u3066\u304a\u308a\u307e\u3059\u3002\n[\u81ea\u5206\u306e\u540d\u524d\u30fb\u90e8\u7f72] \u306e[\u81ea\u5206\u306e\u540d\u524d] \u3068\u7533\u3057\u307e\u3059\u3002\n\n\u5148\u307b\u3069\u3054\u9023\u7d61\u3044\u305f\u3060\u3044\u305f\u6765\u9031\u706b\u66dc\u65e5\u306e\u6253\u3061\u5408\u308f\u305b\u306b\u3064\u3044\u3066\u3001\u4ee5\u4e0b\u306e\u901a\u308a\u6c34\u66dc\u65e5\u306b\u5909\u66f4\u3057\u3066\u3044\u305f\u3060\u304f\u3053\u3068\u306b\u306a\u308a\u307e\u3057\u305f\u306e\u3067\u3001\u3054\u78ba\u8a8d\u304f\u3060\u3055\u3044\u3002\n\n**\u5909\u66f4\u5185\u5bb9**\n- **\u539f\u65e5\u7a0b**\uff1a\u6765\u9031\uff08\u3007\u6708\u3007\u65e5\uff09\u706b\u66dc\u65e5\n- **\u65b0\u65e5\u7a0b**\uff1a\u6765\u9031\uff08\u3007\u6708\u3007\u65e5\uff09\u6c34\u66dc\u65e5\n\n\u3053\u306e\u5909\u66f4\u306f\u3001[\u7406\u7531\u3084\u7406\u7531\u306e\u8aac\u660e] \u306b\u3088\u308b\u3082\u306e\u3067\u3042\u308a\u3001[\u5177\u4f53\u7684\u306a\u7406\u7531] \u3092\u8e0f\u307e\u3048\u3066\u6c7a\u5b9a\u3044\u305f\u3057\u307e\u3057\u305f\u3002\n\n\u3054\u78ba\u8a8d\u306e\u4e0a\u3001\u3088\u308d\u3057\u304f\u304a\u9858\u3044\u3044\u305f\u3057\u307e\u3059\u3002\n\u307e\u305f\u3001\u5909\u66f4\u5f8c\u306e\u8a73\u7d30\u306a\u30b9\u30b1\u30b8\u30e5\u30fc\u30eb\u3084\u8cc7\u6599\u7b49\u304c\u5fc5\u8981\u3067\u3042\u308c\u3070\u3001\u304a\u6c17\u8efd\u306b\u304a\u7533\u3057\u4ed8\u3051\u304f\u3060\u3055\u3044\u3002\n\n\u656c\u5177\n\n[\u81ea\u5206\u306e\u7f72\u540d]\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\">\u307e\u305a\u3001\u308a\u3093\u3054\u306e\u4ee3\u91d1\u3068\u307f\u304b\u3093\u306e\u4ee3\u91d1\u3092\u8a08\u7b97\u3057\u307e\u3059\u3002\n\n- \u308a\u3093\u3054\uff1a1\u500b120\u5186 \u00d7 3\u500b = 360\u5186  \n- \u307f\u304b\u3093\uff1a1\u500b45\u5186 \u00d7 8\u500b = 360\u5186  \n\n\u5408\u8a08\u3067 360\u5186 + 360\u5186 = **720\u5186**  \n\n\u652f\u6255\u3063\u305f\u91d1\u984d\u306f 1,000\u5186\u672d\u306a\u306e\u3067\u3001\u6255\u3044\u6b8b\u308a\uff08\u304a\u3064\u308a\uff09\u984d\u306f  \n\n1,000\u5186 \u2212 720\u5186 = **280\u5186**  \n\n\u3057\u305f\u304c\u3063\u3066\u3001\u304a\u3064\u308a\u306f **280\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\u306b\u306f\u6d77\u306b\u9762\u3057\u3066\u3044\u306a\u3044\uff08\u5185\u9678\u306b\u3042\u308b\uff09\u90fd\u9053\u5e9c\u770c\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3067\u3059\u3002\n\n- \u6771\u4eac\u90fd\uff08\u6771\u4eac\u6e7e\u5cb8\u6cbf\u5cb8\u90e8\u306f\u6d77\u306b\u9762\u3057\u3066\u3044\u308b\u304c\u3001\u5185\u9678\u90e8\u3082\u542b\u3080\u305f\u3081\u300c\u6d77\u306b\u9762\u3057\u3066\u3044\u306a\u3044\u300d\u3068\u8a00\u3048\u308b\u304b\u306f\u8b70\u8ad6\u3042\u308a\uff09\n- \u5317\u6d77\u9053\uff08\u5168\u57df\u304c\u5185\u9678\uff09\n- \u9759\u5ca1\u770c\uff08\u5185\u9678\u90e8\u304c\u4e2d\u5fc3\u3067\u6d77\u5cb8\u7dda\u306f\u6975\u3081\u3066\u77ed\u3044\uff09\n- \u5c90\u961c\u770c\uff08\u5185\u9678\uff09\n- \u611b\u77e5\u770c\uff08\u5185\u9678\u90e8\u5206\u304c\u5927\u304d\u3044\uff09\n- \u6ecb\u8cc0\u770c\uff08\u5185\u9678\uff09\n- \u4eac\u90fd\u5e9c\uff08\u5185\u9678\uff09\n- \u5927\u962a\u5e9c\uff08\u5185\u9678\uff09\n- \u5948\u826f\u770c\uff08\u5185\u9678\uff09\n- \u5175\u5eab\u770c\uff08\u5185\u9678\u90e8\u5206\u3042\u308a\uff09\n- \u795e\u5948\u5ddd\u770c\uff08\u5185\u9678\u90e8\u5206\u3042\u308a\uff09\n- \u57fc\u7389\u770c\uff08\u5185\u9678\uff09\n- \u5343\u8449\u770c\uff08\u5185\u9678\u90e8\u5206\u3042\u308a\uff09\n- \u7fa4\u99ac\u770c\uff08\u5185\u9678\uff09\n- \u6803\u5c71\u770c\uff08\u5185\u9678\uff09\n- \u5c71\u68a8\u770c\uff08\u5185\u9678\uff09\n- \u9577\u91ce\u770c\uff08\u5185\u9678\uff09\n- \u5bcc\u5c71\u770c\uff08\u5185\u9678\u90e8\u5206\u3042\u308a\uff09\n- \u77f3\u5ddd\u770c\uff08\u5185\u9678\u90e8\u5206\u3042\u308a\uff09\n- \u798f\u4e95\u770c\uff08\u5185\u9678\uff09\n- \u5c90\u961c\u770c\uff08\u4e0a\u8a18\u306b\u542b\u307e\u308c\u308b\uff09\n- \u611b\u5a9b\u770c\uff08\u5185\u9678\u90e8\u5206\u3042\u308a\uff09\n- \u5bae\u5d0e\u770c\uff08\u5185\u9678\uff09\n- \u5927\u5206\u770c\uff08\u5185\u9678\uff09\n- \u718a\u672c\u770c\uff08\u5185\u9678\uff09\n- \u9e7f\u5150\u5cf6\u770c\uff08\u5185\u9678\uff09\n\n\u305f\u3060\u3057\u3001**\u300c\u6d77\u306b\u9762\u3057\u3066\u3044\u306a\u3044\u300d\u3068\u8a00\u3048\u308b\u304b\u3069\u3046\u304b\u306f\u3001\u5404\u770c\u306e\u5883\u754c\u7dda\u3084\u5730\u5f62\u306b\u3088\u3063\u3066\u7570\u306a\u308a\u307e\u3059**\u3002\u4f8b\u3048\u3070\u3001\u6771\u4eac\u90fd\u306f\u6771\u4eac\u6e7e\u5cb8\u6cbf\u5cb8\u90e8\u304c\u6d77\u306b\u9762\u3057\u3066\u3044\u307e\u3059\u304c\u3001\u5c71\u624b\u5e73\u91ce\u306a\u3069\u306e\u5185\u9678\u90e8\u3082\u542b\u307f\u307e\u3059\u3002\n\n\u6b63\u78ba\u306a\u30ea\u30b9\u30c8\u3092\u63d0\u793a\u3059\u308b\u306b\u306f\u3001\u6700\u65b0\u306e\u884c\u653f\u533a\u5206\u3084\u5730\u7406\u60c5\u5831\u304c\u5fc5\u8981\u3067\u3059\u3002\u4e00\u822c\u7684\u306a\u77e5\u8b58\u3068\u3057\u3066\u3001**\u300c\u6d77\u306b\u9762\u3057\u3066\u3044\u306a\u3044\u770c\u300d**\u3068\u3057\u3066\u306f\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u3082\u306e\u304c\u6319\u3052\u3089\u308c\u307e\u3059\uff1a\n\n- \u5317\u6d77\u9053\n- \u9759\u5ca1\u770c\uff08\u4e00\u90e8\uff09\n- \u5c90\u961c\u770c\n- \u611b\u77e5\u770c\uff08\u4e00\u90e8\uff09\n- \u6ecb\u8cc0\u770c\n- \u4eac\u90fd\u5e9c\n- \u5927\u962a\u5e9c\n- \u5948\u826f\u770c\n- \u5175\u5eab\u770c\uff08\u4e00\u90e8\uff09\n- \u795e\u5948\u5ddd\u770c\uff08\u4e00\u90e8\uff09\n- \u57fc\u7389\u770c\n- \u5343\u8449\u770c\uff08\u4e00\u90e8\uff09\n- \u7fa4\u99ac\u770c\n- \u5c71\u68a8\u770c\n- \u9577\u91ce\u770c\n- \u5bcc\u5c71\u770c\uff08\u4e00\u90e8\uff09\n- \u77f3\u5ddd\u770c\uff08\u4e00\u90e8\uff09\n- \u798f\u4e95\u770c\n\n\u305f\u3060\u3057\u3001\u3053\u308c\u306f\u5b8c\u5168\u306a\u30ea\u30b9\u30c8\u3067\u306f\u306a\u304f\u3001**\u300c\u6d77\u306b\u9762\u3057\u3066\u3044\u306a\u3044\u300d\u3068\u8a00\u3048\u308b\u304b\u3069\u3046\u304b\u306f\u5404\u770c\u306e\u5883\u754c\u7dda\u3084\u5730\u5f62\u306b\u3088\u3063\u3066\u7570\u306a\u308a\u307e\u3059**\u3002\u6b63\u78ba\u306a\u60c5\u5831\u3092\u5f97\u308b\u306b\u306f\u3001\u5404\u90fd\u9053\u5e9c\u770c\u306e\u884c\u653f\u533a\u5206\u3084\u5730\u7406\u30c7\u30fc\u30bf\u3092\u53c2\u7167\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\n\n\u3082\u3057\u5177\u4f53\u7684\u306a\u6761\u4ef6\uff08\u4f8b\uff1a\u6d77\u5cb8\u7dda\u304c\u306a\u3044\u304b\u3001\u5185\u9678\u90e8\u306e\u307f\u306a\u3069\uff09\u304c\u3042\u308c\u3070\u3001\u3088\u308a\u6b63\u78ba\u306b\u7b54\u3048\u308b\u3053\u3068\u304c\u3067\u304d\u307e\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\">**1. \u6625\u306e\u82b1\u958b\u304d**  \n*\u4e94\u30fb\u4e03\u30fb\u4e94*\uff085-7-5\uff09  \n\u300c\u685c\u304c\u54b2\u304f\u3000\u6625\u306e\u98a8\u306b\u3000\u821e\u3046\u300d  \n**\u8aac\u660e**\uff1a\u685c\u306e\u82b1\u304c\u54b2\u304d\u3001\u6625\u306e\u98a8\u306b\u4e57\u3063\u3066\u821e\u3046\u69d8\u5b50\u3092\u8a60\u3093\u3060\u3002\u6625\u306e\u8a2a\u308c\u3068\u7f8e\u3057\u3055\u3092\u8868\u73fe\u3002\n\n---\n\n**2. \u5ddd\u306e\u305b\u305b\u3089\u304e**  \n*\u4e94\u30fb\u4e03\u30fb\u4e94*\uff085-7-5\uff09  \n\u300c\u6c34\u306e\u97f3\u3000\u6625\u306e\u5ddd\u3000\u6d41\u308c\u308b\u300d  \n**\u8aac\u660e**\uff1a\u6625\u306e\u5ddd\u306e\u305b\u305b\u3089\u304e\u306e\u97f3\u3092\u63cf\u304d\u3001\u81ea\u7136\u306e\u9759\u3051\u3055\u3068\u6d41\u308c\u3092\u8868\u73fe\u3002\n\n---\n\n**3. \u9ce5\u306e\u3055\u3048\u305a\u308a**  \n*\u4e94\u30fb\u4e03\u30fb\u4e94*\uff085-7-5\uff09  \n\u300c\u5c0f\u9ce5\u304c\u6b4c\u3046\u3000\u6625\u306e\u7a7a\u3000\u8272\u300d  \n**\u8aac\u660e**\uff1a\u6625\u306e\u7a7a\u306b\u5c0f\u9ce5\u304c\u6b4c\u3044\u3001\u8272\u9bae\u3084\u304b\u306a\u666f\u8272\u3092\u63cf\u3044\u305f\u3002\u81ea\u7136\u306e\u97f3\u3068\u7f8e\u3057\u3055\u3092\u8868\u73fe\u3002\n<\/code><\/pre>\n<p><!-- \/lmw:lab --><\/p>\n<p><!-- lmw:peers --><\/p>\n<h2>Recent Models in the Same Size Class<\/h2>\n<p><em>Models with <\/em><em>up to 4B<\/em><em> parameters that Local Model Watch covered recently, listed by code from our article log for comparison. VRAM tiers are this site&#8217;s estimates; licenses are as stated on the model cards.<\/em><\/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>Parameters<\/th>\n<th>Smallest VRAM tier<\/th>\n<th>License<\/th>\n<th>Our article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>AtomicChat\/Aion-1.0-Instruct-2.3B-GGUF<\/td>\n<td>2.3B<\/td>\n<td>4GB<\/td>\n<td>mit<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/19\/aion-1-0-instruct-2-3b-gguf-released\/\">Aion-1.0-Instruct-2.3B-GGUF 2.3B Text Generation Model: 4GB+ VRAM<\/a> (2026-11-18)<\/td>\n<\/tr>\n<tr>\n<td>openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark-gguf<\/td>\n<td>389M<\/td>\n<td>4GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/minicpm-v-4-7-35b-a3b-dspark-gguf-2\/\">MiniCPM-V-4.7-35B-A3B-DSpark-gguf Draft Model for Speedup: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>openbmb\/MiniCPM-V-4.7-1B-DSpark-gguf<\/td>\n<td>214M<\/td>\n<td>4GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/minicpm-v-4-7-1b-dspark-gguf-released\/\">MiniCPM-V-4.7-1B-DSpark-gguf Text Generation Model: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>IFM\/Jais-3-0.9B-GGUF<\/td>\n<td>1.1B<\/td>\n<td>4GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/jais-3-0-9b-gguf-released\/\">Jais-3-0.9B-GGUF Bilingual Dense Model: Our Test Answers, 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>nvidia\/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16<\/td>\n<td>4.0B<\/td>\n<td>4GB<\/td>\n<td>openmdw-1.1<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-dory-1-0-4b-recurrent-llm\/\">NVIDIA Releases Dory1.0-4B: A Recurrent 4B LLM with Dynamic Loops<\/a> (2026-11-17)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:peers --><\/p>\n<h2>How to Get It<\/h2>\n<p>This model is available in GGUF format at the Hugging Face repository &#8220;<a href=\"https:\/\/huggingface.co\/ggml-org\/LFM3-1.7B-GGUF\">ggml-org\/LFM3-1.7B-GGUF<\/a>&#8220;. It is not a gated model that requires agreement to a license upon download.<\/p>\n<p>If using llama.app, you can load the model and start the server with the following command:<\/p>\n<pre><code class=\"language-bash\">llama serve -hf ggml-org\/LFM3-1.7B-GGUF\n<\/code><\/pre>\n<p>Note that running this model requires a build environment for <code>llama.cpp<\/code> that supports the LFM3 architecture. Supported engines include <code>llama.cpp<\/code>, as well as Ollama and LM Studio.<\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquidai-lfm3-17b-mlx-5bit\/\">LFM3-1.7B-MLX-5bit Text Generation Model: 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/ggml-org-releases-tinylfm3-omni-for-testing-gguf\/\">ggml-org Releases tinyLFM3-Omni-for-testing-gguf for CI<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/18\/kokoro-82m-gguf-released\/\">Kokoro-82M-GGUF Lightweight Text-to-Speech Model: File List<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/qwen3-5-4b-gguf-released\/\">Qwen3.5-4B-GGUF Vision-Language Model: Our Test Answers, 4GB+ 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 4GB tier) \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-8gb-en\/\">Other models that run on a 8GB GPU<\/a><\/li>\n<li><strong>Explore the same model family<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-liquidai-lfm3-en\/\">LFM3 family overview (2 articles)<\/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>Formats this model is available in<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF format guide and models<\/a><\/li>\n<li><strong>Learn about the publisher<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-liquidai-en\/\">Liquid AI: 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\/LFM3-1.7B-GGUF\">https:\/\/huggingface.co\/ggml-org\/LFM3-1.7B-GGUF<\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/LiquidAI\/LFM3-1.7B\">https:\/\/huggingface.co\/LiquidAI\/LFM3-1.7B<\/a><\/li>\n<\/ul>\n<p><!-- lmw:updates --><\/p>\n<h2>Update History<\/h2>\n<ul>\n<li>2026-11-19: Added our own measurements: Japanese token efficiency, what is inside the GGUF file, CPU speed and answers to Japanese questions.<\/li>\n<li>2026-11-19: Changed the title to show what the article covers (VRAM requirements, file list, etc.).<\/li>\n<\/ul>\n<p><!-- \/lmw:updates --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>LiquidAI&#8217;s LFM3-1.7B, an agent-focused model with a 256K context window, is now available in GGUF format via ggml-org for local execution.<\/p>\n","protected":false},"author":1,"featured_media":19906,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[310],"tags":[161,1970,163,4177,5363,2278,1073,1547,1555],"class_list":["post-19470","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-models","tag-ggml-en","tag-ggml-org-en","tag-gguf-en","tag-lfm3-en","tag-lfm3-1-7b-gguf-en","tag-liquidai-en","tag-llama-cpp-en","tag-verified","tag--en"],"lang":"en","translations":{"en":19470,"ja":19468},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/19470","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=19470"}],"version-history":[{"count":5,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/19470\/revisions"}],"predecessor-version":[{"id":20268,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/19470\/revisions\/20268"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/19906"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=19470"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=19470"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=19470"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}