<?xml version="1.0" encoding="UTF-8"?><feed xmlns="http://www.w3.org/2005/Atom"><title>ggufmodels.com: newest GGUF models</title><subtitle>New GGUF language models on Hugging Face, with sizes and memory needs.</subtitle><link rel="self" href="https://ggufmodels.com/feed.xml"/><link href="https://ggufmodels.com/"/><id>https://ggufmodels.com/</id><updated>2026-11-15T23:02:47.000Z</updated><entry><title>tiny aya wazuh analyst GGUF v2a (GGUF by Yusheng88)</title><link href="https://ggufmodels.com/model/tiny-aya-wazuh-analyst-v2a-by-yusheng88"/><id>https://ggufmodels.com/model/tiny-aya-wazuh-analyst-v2a-by-yusheng88</id><updated>2026-11-15T23:02:47.000Z</updated><summary>tiny aya wazuh analyst GGUF v2a, a Tiny model: 3.35B parameters, 8K context, Q4_K_M file 2.1 GB.</summary></entry><entry><title>tiny aya sms extract (GGUF by Meowniece)</title><link href="https://ggufmodels.com/model/tiny-aya-sms-extract-by-meowniece"/><id>https://ggufmodels.com/model/tiny-aya-sms-extract-by-meowniece</id><updated>2026-11-15T22:15:38.000Z</updated><summary>tiny aya sms extract, a Tiny model: 3.35B parameters, 8K context, smallest file 3.6 GB.</summary></entry><entry><title>pii masker qwen3 4b (GGUF by Zain9989)</title><link href="https://ggufmodels.com/model/pii-masker-qwen3-4b-by-zain9989"/><id>https://ggufmodels.com/model/pii-masker-qwen3-4b-by-zain9989</id><updated>2026-11-15T17:32:23.000Z</updated><summary>pii masker qwen3 4b, a Qwen model: 4.02B parameters, 256K context, Q4_K_M file 2.5 GB.</summary></entry><entry><title>taleemabad offline teacher coach 2b (GGUF by oyekamal)</title><link href="https://ggufmodels.com/model/taleemabad-offline-teacher-coach-2b-by-oyekamal"/><id>https://ggufmodels.com/model/taleemabad-offline-teacher-coach-2b-by-oyekamal</id><updated>2026-11-15T17:02:40.000Z</updated><summary>taleemabad offline teacher coach 2b, a Qwen model: 1.88B parameters, 256K context, Q4_K_M file 1.3 GB.</summary></entry><entry><title>nulleon diretor criativo v2 (GGUF by nulleon)</title><link href="https://ggufmodels.com/model/nulleon-diretor-criativo-v2-by-nulleon"/><id>https://ggufmodels.com/model/nulleon-diretor-criativo-v2-by-nulleon</id><updated>2026-11-15T17:01:37.000Z</updated><summary>nulleon diretor criativo v2, a Qwen model: 7.62B parameters, 32K context, Q4_K_M file 4.7 GB.</summary></entry><entry><title>glossa qwen3 0.6b (GGUF by glossareader)</title><link href="https://ggufmodels.com/model/glossa-qwen3-0-6b-by-glossareader"/><id>https://ggufmodels.com/model/glossa-qwen3-0-6b-by-glossareader</id><updated>2026-11-15T16:43:54.000Z</updated><summary>glossa qwen3 0.6b, a Qwen model: 596M parameters, 40K context, smallest file 0.6 GB.</summary></entry><entry><title>mise ft gemma4 e2b (GGUF by ArashNasr)</title><link href="https://ggufmodels.com/model/mise-ft-gemma4-e2b-by-arashnasr"/><id>https://ggufmodels.com/model/mise-ft-gemma4-e2b-by-arashnasr</id><updated>2026-11-15T15:41:38.000Z</updated><summary>mise ft gemma4 e2b, a Gemma model: 5.1B parameters, 128K context, Q4_K_M file 4.4 GB.</summary></entry><entry><title>fabula story planner 1b (GGUF by DeadEagle001)</title><link href="https://ggufmodels.com/model/fabula-story-planner-1b-by-deadeagle001"/><id>https://ggufmodels.com/model/fabula-story-planner-1b-by-deadeagle001</id><updated>2026-11-15T12:50:30.000Z</updated><summary>fabula story planner 1b, a Fabula model: 1.24B parameters, 128K context, Q4_K_M file 0.8 GB.</summary></entry><entry><title>Qwen3.5 4B 45pct 3ep Gguf (GGUF by lancerChua)</title><link href="https://ggufmodels.com/model/qwen3-5-4b-45pct-3ep-by-lancerchua"/><id>https://ggufmodels.com/model/qwen3-5-4b-45pct-3ep-by-lancerchua</id><updated>2026-11-15T12:30:40.000Z</updated><summary>Qwen3.5 4B 45pct 3ep Gguf, a Qwen model: 4.33B parameters, 256K context, smallest file 4.6 GB.</summary></entry><entry><title>qwen 3.5 4B decision 16bit (GGUF by Nullmega)</title><link href="https://ggufmodels.com/model/qwen-3-5-4b-decision-16bit-by-nullmega"/><id>https://ggufmodels.com/model/qwen-3-5-4b-decision-16bit-by-nullmega</id><updated>2026-11-15T06:15:01.000Z</updated><summary>qwen 3.5 4B decision 16bit, a Qwen model: 4.24B parameters, 256K context, Q4_K_M file 2.7 GB.</summary></entry><entry><title>canyon racer lfm2 230m v1.5 (GGUF by aldigobbler)</title><link href="https://ggufmodels.com/model/canyon-racer-lfm2-230m-v1-5-by-aldigobbler"/><id>https://ggufmodels.com/model/canyon-racer-lfm2-230m-v1-5-by-aldigobbler</id><updated>2026-11-15T01:57:51.000Z</updated><summary>canyon racer lfm2 230m v1.5, a Lfm model: 230M parameters, 125K context, Q4_K_M file 0.2 GB.</summary></entry><entry><title>Ornith 1.5 35B A3B (GGUF by Xylolabs)</title><link href="https://ggufmodels.com/model/ornith-1-5-35b-a3b-by-xylolabs"/><id>https://ggufmodels.com/model/ornith-1-5-35b-a3b-by-xylolabs</id><updated>2026-11-15T01:32:24.000Z</updated><summary>Ornith 1.5 35B A3B, a Ornith model: 35.5B parameters, 256K context, Q4_K_M file 21.7 GB.</summary></entry><entry><title>Qwen38 27b Topocbp Bf16 Merged (GGUF by frankmorales2020)</title><link href="https://ggufmodels.com/model/qwen3-8-27b-topocbp-by-frankmorales2020"/><id>https://ggufmodels.com/model/qwen3-8-27b-topocbp-by-frankmorales2020</id><updated>2026-11-14T21:17:47.000Z</updated><summary>Qwen38 27b Topocbp Bf16 Merged, a Qwen model: 26.9B parameters, 256K context, smallest file 28.6 GB.</summary></entry><entry><title>NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 (GGUF by Xylolabs)</title><link href="https://ggufmodels.com/model/nvidia-nemotron-3-5-lightning-30b-a3b-by-xylolabs"/><id>https://ggufmodels.com/model/nvidia-nemotron-3-5-lightning-30b-a3b-by-xylolabs</id><updated>2026-11-14T18:06:57.000Z</updated><summary>NVIDIA Nemotron 3.5 Lightning 30B A3B BF16, a Nemotron model: 32.9B parameters, 1024K context, Q4_K_M file 25.4 GB.</summary></entry><entry><title>NVIDIA Nemotron 3 Nano 30B A3B BF16 (GGUF by Xylolabs)</title><link href="https://ggufmodels.com/model/nvidia-nemotron-3-nano-30b-a3b-by-xylolabs"/><id>https://ggufmodels.com/model/nvidia-nemotron-3-nano-30b-a3b-by-xylolabs</id><updated>2026-11-14T18:04:19.000Z</updated><summary>NVIDIA Nemotron 3 Nano 30B A3B BF16, a Nemotron model: 31.6B parameters, 1024K context, Q4_K_M file 24.5 GB.</summary></entry><entry><title>Qwen3.8 4B Empero FullStack Decensored MTP Q4 K M (GGUF by hUh63)</title><link href="https://ggufmodels.com/model/qwen3-8-4b-empero-fullstack-decensored-mtp-q4-k-m-by-huh63"/><id>https://ggufmodels.com/model/qwen3-8-4b-empero-fullstack-decensored-mtp-q4-k-m-by-huh63</id><updated>2026-11-14T17:59:52.000Z</updated><summary>Qwen3.8 4B Empero FullStack Decensored MTP Q4 K M, a Qwen model: 334M parameters, 256K context, Q4_K_M file 2.9 GB.</summary></entry><entry><title>Qwen3.5 9B (GGUF by BaherMH)</title><link href="https://ggufmodels.com/model/qwen3-5-9b-by-bahermh"/><id>https://ggufmodels.com/model/qwen3-5-9b-by-bahermh</id><updated>2026-11-14T17:26:11.000Z</updated><summary>Qwen3.5 9B, a Qwen model: 9.2B parameters, 256K context, Q4_K_M file 5.8 GB.</summary></entry><entry><title>Qwen3.8 35B A3B Hierophant 1.0 (GGUF by hhjuyh)</title><link href="https://ggufmodels.com/model/qwen3-8-35b-a3b-hierophant-1-0-by-hhjuyh"/><id>https://ggufmodels.com/model/qwen3-8-35b-a3b-hierophant-1-0-by-hhjuyh</id><updated>2026-11-14T15:58:22.000Z</updated><summary>Qwen3.8 35B A3B Hierophant 1.0, a Qwen model: 35.5B parameters, 256K context, Q4_K_M file 21.7 GB.</summary></entry><entry><title>Lin 1 Epsilon (GGUF by LindotAI)</title><link href="https://ggufmodels.com/model/lin-1-epsilon-by-lindotai"/><id>https://ggufmodels.com/model/lin-1-epsilon-by-lindotai</id><updated>2026-11-14T15:50:02.000Z</updated><summary>Lin 1 Epsilon, a Lin model: 494M parameters, 32K context, Q4_K_M file 0.4 GB.</summary></entry><entry><title>model (GGUF by senthilsk)</title><link href="https://ggufmodels.com/model/model-by-senthilsk"/><id>https://ggufmodels.com/model/model-by-senthilsk</id><updated>2026-11-14T15:26:22.000Z</updated><summary>model, a Model model: 8.03B parameters, 128K context, Q4_K_M file 4.9 GB.</summary></entry><entry><title>Jeffan 4B 2010 (GGUF by tattrongvu)</title><link href="https://ggufmodels.com/model/jeffan-4b-2010-by-tattrongvu"/><id>https://ggufmodels.com/model/jeffan-4b-2010-by-tattrongvu</id><updated>2026-11-14T15:12:35.000Z</updated><summary>Jeffan 4B 2010, a Jeffan model: 4.21B parameters, 256K context, Q4_K_M file 2.7 GB.</summary></entry><entry><title>MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking (GGUF by ITLL)</title><link href="https://ggufmodels.com/model/minicpm5-1b-claude-opus-fable5-v2-thinking-by-itll"/><id>https://ggufmodels.com/model/minicpm5-1b-claude-opus-fable5-v2-thinking-by-itll</id><updated>2026-11-14T09:34:08.000Z</updated><summary>MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking, a MiniCPM model: 1.08B parameters, 128K context, smallest file 1.2 GB.</summary></entry><entry><title>embeddinggemma2 Q8 0 (GGUF by TszAstrea)</title><link href="https://ggufmodels.com/model/embeddinggemma2-q8-0-by-tszastrea"/><id>https://ggufmodels.com/model/embeddinggemma2-q8-0-by-tszastrea</id><updated>2026-11-14T04:30:32.000Z</updated><summary>embeddinggemma2 Q8 0, a Embeddinggemma model: 271M parameters, 256K context, smallest file 0.3 GB.</summary></entry><entry><title>Qwen3.8 27B GSQ RCO IQ3 XXS Uncensored (GGUF by andrevp)</title><link href="https://ggufmodels.com/model/qwen3-8-27b-gsq-rco-iq3-xxs-uncensored-by-andrevp"/><id>https://ggufmodels.com/model/qwen3-8-27b-gsq-rco-iq3-xxs-uncensored-by-andrevp</id><updated>2026-11-14T01:53:26.000Z</updated><summary>Qwen3.8 27B GSQ RCO IQ3 XXS Uncensored, a Qwen model: 27.3B parameters, 256K context, smallest file 10.5 GB.</summary></entry><entry><title>Huihui Qwen3.8 27B Abliterated (GGUF by andrevp)</title><link href="https://ggufmodels.com/model/huihui-qwen3-8-27b-abliterated-by-andrevp"/><id>https://ggufmodels.com/model/huihui-qwen3-8-27b-abliterated-by-andrevp</id><updated>2026-11-14T01:46:43.000Z</updated><summary>Huihui Qwen3.8 27B Abliterated, a Qwen model: 27.3B parameters, 256K context, smallest file 16.8 GB.</summary></entry><entry><title>NVIDIA-Nemotron-3.5-Bolt-E4B (GGUF by WorkOffline)</title><link href="https://ggufmodels.com/model/nvidia-nemotron-3-5-bolt-e4b-ud-by-workoffline"/><id>https://ggufmodels.com/model/nvidia-nemotron-3-5-bolt-e4b-ud-by-workoffline</id><updated>2026-11-13T21:42:14.000Z</updated><summary>NVIDIA-Nemotron-3.5-Bolt-E4B, a Nemotron model: 7.52B parameters, 128K context, smallest file 5.1 GB.</summary></entry><entry><title>Evaryx Core (GGUF by EvaryxTechnologies)</title><link href="https://ggufmodels.com/model/evaryx-core-by-evaryxtechnologies"/><id>https://ggufmodels.com/model/evaryx-core-by-evaryxtechnologies</id><updated>2026-11-13T20:45:43.000Z</updated><summary>Evaryx Core, a Evaryx model: 7.62B parameters, 32K context, smallest file 8.1 GB.</summary></entry><entry><title>qwen3 tts 0.6b android (GGUF by luweigen)</title><link href="https://ggufmodels.com/model/qwen3-tts-0-6b-android-by-luweigen"/><id>https://ggufmodels.com/model/qwen3-tts-0-6b-android-by-luweigen</id><updated>2026-11-13T20:18:53.000Z</updated><summary>qwen3 tts 0.6b android, a Qwen model: 79M parameters, 64 context, smallest file 0.0 GB.</summary></entry><entry><title>Curio 1.5B (GGUF by Bedirhn77)</title><link href="https://ggufmodels.com/model/curio-1-5b-by-bedirhn77"/><id>https://ggufmodels.com/model/curio-1-5b-by-bedirhn77</id><updated>2026-11-13T19:03:12.000Z</updated><summary>Curio 1.5B, a Qwen model: 1.54B parameters, 32K context, smallest file 1.6 GB.</summary></entry><entry><title>qwen3 1.7b planner smoke grpo (GGUF by darcyyao)</title><link href="https://ggufmodels.com/model/qwen3-1-7b-planner-smoke-grpo-by-darcyyao"/><id>https://ggufmodels.com/model/qwen3-1-7b-planner-smoke-grpo-by-darcyyao</id><updated>2026-11-13T18:20:31.000Z</updated><summary>qwen3 1.7b planner smoke grpo, a Qwen model: 1.72B parameters, 40K context, Q4_K_M file 1.1 GB.</summary></entry><entry><title>Huihui Qwen3.8 Flash Next abliterated v2 (GGUF by artificialpossum)</title><link href="https://ggufmodels.com/model/huihui-qwen3-8-flash-next-abliterated-v2-by-artificialpossum"/><id>https://ggufmodels.com/model/huihui-qwen3-8-flash-next-abliterated-v2-by-artificialpossum</id><updated>2026-11-13T18:10:17.000Z</updated><summary>Huihui Qwen3.8 Flash Next abliterated v2, a Qwen model: 177B parameters, 256K context, smallest file 83.7 GB.</summary></entry><entry><title>Qwen2.5 32B Instruct SOM Heretic (GGUF by richardyoung)</title><link href="https://ggufmodels.com/model/qwen2-5-32b-instruct-som-heretic-by-richardyoung"/><id>https://ggufmodels.com/model/qwen2-5-32b-instruct-som-heretic-by-richardyoung</id><updated>2026-11-13T17:57:42.000Z</updated><summary>Qwen2.5 32B Instruct SOM Heretic, a Qwen model: 32.8B parameters, 32K context, Q4_K_M file 19.9 GB.</summary></entry><entry><title>Qwen3 1.7B dpo ultrafeedback binarized 16bit (GGUF by FrancescoArno94)</title><link href="https://ggufmodels.com/model/qwen3-1-7b-dpo-ultrafeedback-binarized-16bit-by-francescoarno94"/><id>https://ggufmodels.com/model/qwen3-1-7b-dpo-ultrafeedback-binarized-16bit-by-francescoarno94</id><updated>2026-11-13T17:48:06.000Z</updated><summary>Qwen3 1.7B dpo ultrafeedback binarized 16bit, a Qwen model: 1.72B parameters, 32K context, smallest file 3.4 GB.</summary></entry><entry><title>qwen3 1.7b planner smoke sft (GGUF by darcyyao)</title><link href="https://ggufmodels.com/model/qwen3-1-7b-planner-smoke-sft-by-darcyyao"/><id>https://ggufmodels.com/model/qwen3-1-7b-planner-smoke-sft-by-darcyyao</id><updated>2026-11-13T17:31:14.000Z</updated><summary>qwen3 1.7b planner smoke sft, a Qwen model: 1.72B parameters, 40K context, Q4_K_M file 1.1 GB.</summary></entry><entry><title>Qwen3 1.7B sft tulu 16bit (GGUF by FrancescoArno94)</title><link href="https://ggufmodels.com/model/qwen3-1-7b-sft-tulu-16bit-by-francescoarno94"/><id>https://ggufmodels.com/model/qwen3-1-7b-sft-tulu-16bit-by-francescoarno94</id><updated>2026-11-13T17:29:43.000Z</updated><summary>Qwen3 1.7B sft tulu 16bit, a Qwen model: 1.72B parameters, 32K context, smallest file 3.4 GB.</summary></entry><entry><title>Qwen3.5-4B (GGUF by fraQtl)</title><link href="https://ggufmodels.com/model/qwen3-5-4b-hi-fi-by-fraqtl"/><id>https://ggufmodels.com/model/qwen3-5-4b-hi-fi-by-fraqtl</id><updated>2026-11-13T15:58:39.000Z</updated><summary>Qwen3.5-4B, a Qwen model: 4.21B parameters, 256K context, smallest file 2.7 GB.</summary></entry><entry><title>lorde tiny aya (GGUF by Oxlino)</title><link href="https://ggufmodels.com/model/lorde-tiny-aya-by-oxlino"/><id>https://ggufmodels.com/model/lorde-tiny-aya-by-oxlino</id><updated>2026-11-13T15:56:45.000Z</updated><summary>lorde tiny aya, a Lorde model: 3.35B parameters, 8K context, Q4_K_M file 2.1 GB.</summary></entry><entry><title>Qwen3 8b Heretic (GGUF by dougm66)</title><link href="https://ggufmodels.com/model/qwen3-8b-heretic-by-dougm66"/><id>https://ggufmodels.com/model/qwen3-8b-heretic-by-dougm66</id><updated>2026-11-13T13:50:20.000Z</updated><summary>Qwen3 8b Heretic, a Qwen model: 8.19B parameters, 40K context, Q4_K_M file 5.0 GB.</summary></entry><entry><title>nirca-mini step 123009 (stock gpt-oss arch, 8 fixed passes, adapter) (GGUF by nirca)</title><link href="https://ggufmodels.com/model/nirca-mini-by-nirca"/><id>https://ggufmodels.com/model/nirca-mini-by-nirca</id><updated>2026-11-13T12:50:35.000Z</updated><summary>nirca-mini step 123009 (stock gpt-oss arch, 8 fixed passes, adapter), a gpt-oss model: 3.78B parameters, 2K context, smallest file 3.0 GB.</summary></entry><entry><title>Qwen3.8 Flash Next Q4 K Tokspur (GGUF by san-digital)</title><link href="https://ggufmodels.com/model/qwen3-8-flash-next-q4-k-tokspur-by-san-digital"/><id>https://ggufmodels.com/model/qwen3-8-flash-next-q4-k-tokspur-by-san-digital</id><updated>2026-11-13T12:26:32.000Z</updated><summary>Qwen3.8 Flash Next Q4 K Tokspur, a Qwen model: 51.8B parameters, 256K context, smallest file 2.8 GB.</summary></entry><entry><title>Spark X2.6 4B Uzbek Uncensored (GGUF by hogoraki)</title><link href="https://ggufmodels.com/model/spark-x2-6-4b-uzbek-uncensored-by-hogoraki"/><id>https://ggufmodels.com/model/spark-x2-6-4b-uzbek-uncensored-by-hogoraki</id><updated>2026-11-13T11:57:52.000Z</updated><summary>Spark X2.6 4B Uzbek Uncensored, a Spark model: 4.11B parameters, 1024K context, Q4_K_M file 2.6 GB.</summary></entry><entry><title>Qwen3 1.7B Stratos Thinking (GGUF by Speaks38)</title><link href="https://ggufmodels.com/model/qwen3-1-7b-stratos-thinking-by-speaks38"/><id>https://ggufmodels.com/model/qwen3-1-7b-stratos-thinking-by-speaks38</id><updated>2026-11-13T11:48:01.000Z</updated><summary>Qwen3 1.7B Stratos Thinking, a Qwen model: 1.72B parameters, 40K context, Q4_K_M file 1.1 GB.</summary></entry><entry><title>Qwen3 1.7B GRPO 16bit DAPO math (GGUF by FrancescoArno94)</title><link href="https://ggufmodels.com/model/qwen3-1-7b-grpo-16bit-dapo-math-by-francescoarno94"/><id>https://ggufmodels.com/model/qwen3-1-7b-grpo-16bit-dapo-math-by-francescoarno94</id><updated>2026-11-13T11:45:07.000Z</updated><summary>Qwen3 1.7B GRPO 16bit DAPO math, a Qwen model: 1.72B parameters, 32K context, smallest file 3.4 GB.</summary></entry><entry><title>RastNus Base 12B (GGUF by PawanKrd)</title><link href="https://ggufmodels.com/model/rastnus-base-12b-by-pawankrd"/><id>https://ggufmodels.com/model/rastnus-base-12b-by-pawankrd</id><updated>2026-11-13T10:33:42.000Z</updated><summary>RastNus Base 12B, a Rastnus model: 11.9B parameters, 256K context, Q4_K_M file 7.4 GB.</summary></entry><entry><title>Qwen3.5-4B-3D-Coder (GGUF by VoltAgen92020)</title><link href="https://ggufmodels.com/model/qwen3-5-4b-3d-coder-by-voltagen92020"/><id>https://ggufmodels.com/model/qwen3-5-4b-3d-coder-by-voltagen92020</id><updated>2026-11-13T10:12:09.000Z</updated><summary>Qwen3.5-4B-3D-Coder, a Qwen model: 4.21B parameters, 256K context, Q4_K_M file 2.7 GB.</summary></entry><entry><title>RastNus Small 5B (GGUF by PawanKrd)</title><link href="https://ggufmodels.com/model/rastnus-small-5b-by-pawankrd"/><id>https://ggufmodels.com/model/rastnus-small-5b-by-pawankrd</id><updated>2026-11-13T09:07:34.000Z</updated><summary>RastNus Small 5B, a Rastnus model: 4.63B parameters, 128K context, Q4_K_M file 3.4 GB.</summary></entry><entry><title>RastNus Tiny 1B (GGUF by PawanKrd)</title><link href="https://ggufmodels.com/model/rastnus-tiny-1b-by-pawankrd"/><id>https://ggufmodels.com/model/rastnus-tiny-1b-by-pawankrd</id><updated>2026-11-13T08:38:28.000Z</updated><summary>RastNus Tiny 1B, a Rastnus model: 1.03B parameters, 128K context, Q4_K_M file 0.7 GB.</summary></entry><entry><title>Qwen3.5-9B (GGUF by lisnapyc)</title><link href="https://ggufmodels.com/model/qwen3-5-9b-q4-k-m-mtp-headq8-by-lisnapyc"/><id>https://ggufmodels.com/model/qwen3-5-9b-q4-k-m-mtp-headq8-by-lisnapyc</id><updated>2026-11-13T07:18:11.000Z</updated><summary>Qwen3.5-9B, a Qwen model: 9.2B parameters, 256K context, Q4_K_M file 5.9 GB.</summary></entry><entry><title>granite 4.0 h 350m router kd web4 s0 (GGUF by martinnavs)</title><link href="https://ggufmodels.com/model/granite-4-0-h-350m-router-kd-web4-s0-by-martinnavs"/><id>https://ggufmodels.com/model/granite-4-0-h-350m-router-kd-web4-s0-by-martinnavs</id><updated>2026-11-13T06:42:23.000Z</updated><summary>granite 4.0 h 350m router kd web4 s0, a Granite model: 340M parameters, 1024K context, Q4_K_M file 0.2 GB.</summary></entry><entry><title>Olmo 3.1 32B Instruct SOM Heretic (GGUF by richardyoung)</title><link href="https://ggufmodels.com/model/olmo-3-1-32b-instruct-som-heretic-by-richardyoung"/><id>https://ggufmodels.com/model/olmo-3-1-32b-instruct-som-heretic-by-richardyoung</id><updated>2026-11-13T05:19:03.000Z</updated><summary>Olmo 3.1 32B Instruct SOM Heretic, a OLMo model: 32.2B parameters, 64K context, Q4_K_M file 19.5 GB.</summary></entry></feed>