{"id":13765,"date":"2026-11-17T11:02:39","date_gmt":"2026-11-17T02:02:39","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=13765"},"modified":"2026-11-17T11:11:47","modified_gmt":"2026-11-17T02:11:47","slug":"liquidai-lfm3-17b-mlx-5bit","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquidai-lfm3-17b-mlx-5bit\/","title":{"rendered":"LFM3-1.7B-MLX-5bit Text Generation Model: 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\/LiquidAI\/LFM3-1.7B-MLX-5bit\">LiquidAI\/LFM3-1.7B-MLX-5bit<\/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>2026-10-27<\/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-mlx-en\/\">MLX<\/a> \/ safetensors<\/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<h2>Overview<\/h2>\n<p>LiquidAI has released &#8220;LFM3-1.7B-MLX-5bit&#8221;, a 5-bit MLX quantization for Apple Silicon of their agent-focused model &#8220;LFM3-1.7B&#8221;.<\/p>\n<p>The base model &#8220;LFM3-1.7B&#8221; is a text generation model developed for agent capabilities and specialized applications running in local environments. It adopts a unique tri-hybrid architecture and can process a long-context window of up to 256K tokens.<\/p>\n<h2>Specifications<\/h2>\n<ul>\n<li>Parameters: 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>Below are the benchmark evaluation results listed in the model card of the source base model &#8220;LFM3-1.7B&#8221;. These scores are actual measured values published by the release source using vLLM, and are figures from the unquantized model. To make the comparison easier to read, some model columns (Qwen3.5 9B) have been omitted from the model card table.<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/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<\/tr>\n<tr>\n<td><strong>Average<\/strong><\/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<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>According to the comparison data in the model card, LFM3-1.7B shows particularly high scores in the fields of agent capabilities, tool use, and instruction following. It recorded 71.39 on BFCL V4, which measures function selection and argument assembly precision, the highest figure among the compared models. It also achieved an excellent score of 96.66 on IFEval, which measures compliance with formatting instructions. It also recorded 43.40 on SWE-bench Verified (OpenCode), which measures the ability to fix real GitHub issues, showing strengths in agentic coding tasks. On the other hand, it stays at 63.37 on GPQA Diamond, which handles PhD-level problems, falling short of Qwen3.5 4B&#8217;s 75.76, and is 65.56 on RULER 128K, which measures long-context effectiveness, resulting in scores that trail competing models in some knowledge and long-context tasks.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>The base model LFM3-1.7B is designed assuming local-environment agent capabilities, tool use, structured outputs, and domain-specific fine-tuning. It supports agent harnesses such as Hermes Agent, Pi, and OpenClaw, and is capable of processing utilizing a 256K token context window. Note that due to the small-scale characteristics of the model, it is not recommended for agentic coding or complex multi-step reasoning. Additionally, combining it with search or information retrieval is recommended for knowledge-intensive tasks.<\/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>MLX 5bit<\/td>\n<td>1.1GB<\/td>\n<td>1.3GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><strong>Inference engine support<\/strong> (architecture name matched against each project&#8217;s own model registry in its source code, checked 2026-11-17): llama.cpp: registered, vLLM: registered, MLX (mlx-lm): not registered. &#8220;Not registered&#8221; means the name is absent from that registry today, not that the model cannot run.<\/p>\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>Not usable in Ollama, LM Studio and llama.cpp yet \u2014 we have found no GGUF build.<\/strong><\/p>\n<p>The publisher ships MLX \/ safetensors only. However, llama.cpp&#8217;s registry does list this architecture, so <strong>conversion to GGUF is possible<\/strong> and the model will run once someone publishes a converted build. Today it can be run with transformers, vLLM or MLX (Apple Silicon), using the memory figures in the table above.<\/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><strong>Compression:<\/strong> the MLX 5bit build measures 5.47 bits per weight \u2014 about 34% 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: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>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: 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<tr>\n<td>LiquidAI\/LFM2.5-24B-A2B-DSpark<\/td>\n<td>328M<\/td>\n<td>4GB<\/td>\n<td>lfm1.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquid-ai-lfm25-24b-a2b-dspark\/\">LFM2.5-24B-A2B-DSpark Speculative Decoding Draft Model: 4GB+ VRAM<\/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<ul>\n<li>Distribution format: MLX, safetensors<\/li>\n<li>Download command:<\/li>\n<\/ul>\n<pre><code class=\"language-bash\">mlx_lm.generate --model LiquidAI\/LFM3-1.7B-MLX-5bit \\\n  --prompt &quot;What is the capital of Australia?&quot; \\\n  --temp 0.1 --top-k 50 --max-tokens 16384\n<\/code><\/pre>\n<ul>\n<li>Supported engines: mlx-lm (support is reported to be in progress)<\/li>\n<\/ul>\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-omni-2b-mlx-4bit-apple-silicon\/\">LFM3-Omni-2B-MLX-4bit Multimodal Model: 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquidai-d1-2b-gguf-2\/\">d1-2B-GGUF Text, Image, and Video Decision-Making Model: 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquidai-lfm2-5-24b-a2b-dspark-gguf\/\">LFM2.5-24B-A2B-DSpark-GGUF Text Generation Model: 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquid-ai-lfm25-24b-a2b-dspark\/\">LFM2.5-24B-A2B-DSpark Speculative Decoding Draft Model: 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>Engines that run this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-vllm-en\/\">vLLM<\/a><\/li>\n<li><strong>Formats this model is available in<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-mlx-en\/\">MLX 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<li><strong>Other models for the same task<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/models-by-task-en\/#task-text\">Other text generation models<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/LiquidAI\/LFM3-1.7B-MLX-5bit\">https:\/\/huggingface.co\/LiquidAI\/LFM3-1.7B-MLX-5bit<\/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","protected":false},"excerpt":{"rendered":"<p>LiquidAI has released LFM3-1.7B-MLX-5bit, a 5-bit MLX quantized version of their agent-focused LFM3-1.7B model optimized for Apple Silicon.<\/p>\n","protected":false},"author":1,"featured_media":13764,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[310],"tags":[505,4177,4179,2278,977,1547,1555],"class_list":["post-13765","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-models","tag-apple-silicon-en","tag-lfm3-en","tag-lfm3-1-7b-en","tag-liquidai-en","tag-mlx-en","tag-verified","tag--en"],"lang":"en","translations":{"en":13765,"ja":13763},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13765","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=13765"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13765\/revisions"}],"predecessor-version":[{"id":17956,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13765\/revisions\/17956"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/13764"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=13765"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=13765"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=13765"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}