Suite à l’analyse des modèles sur le PC.
Liste des GGUF :
| Nom | Date de copie | Date du modèle | Taille en Go | Description |
|---|---|---|---|---|
| gemma-3-12b-it-Q4_K_M.gguf | 2026-09-22 | 2026-07-16 | 6,80 | Google Gemma 3 12B Instruct, quantization Q4_K_M |
| gemma-3-12b-mmproj-F16.gguf | 2026-09-22 | 2026-07-16 | 0,80 | Projet multimodal Gemma 3 12B, F16 |
| gemma-3-1b-it-q4_k_m.gguf | 2026-09-22 | 2026-07-16 | 0,75 | Google Gemma 3 1B Instruct, quantization Q4_K_M |
| LFM2.5-VL-3B-Q8_0.gguf | 2026-09-30 | 2026-07-28 | 2,68 | LFM 2.5 Vision Language 3B, quantization Q8_0 |
| Llama-3.2-11B-Vision-Instruct-mmproj.f16.gguf | 2026-09-22 | 2026-07-17 | 1,81 | Meta Llama 3.2 11B Vision Instruct, projet multimodal F16 |
| Llama-3.2-11B-Vision-Instruct.Q4_K_M.gguf | 2026-09-22 | 2026-07-17 | 5,55 | Meta Llama 3.2 11B Vision Instruct, quantization Q4_K_M |
| mmproj-BF16(1).gguf | 2026-09-22 | 2026-07-16 | 0,87 | Projet multimodal, BF16 |
| mmproj-BF16.gguf | 2026-09-22 | 2026-07-17 | 0,87 | Projet multimodal, BF16 |
| mmproj-F16.gguf | 2026-09-22 | 2026-07-17 | 0,86 | Projet multimodal, F16 |
| mmproj-F32.gguf | 2026-09-22 | 2026-07-17 | 2,22 | Projet multimodal, F32 |
| mmproj-LFM2.5-VL-3B-Q8_0.gguf | 2026-09-30 | 2026-07-28 | 0,54 | Projet multimodal LFM 2.5 VL 3B, quantization Q8_0 |
| phi4-mm-Q4_K_M.gguf | 2026-09-29 | 2026-07-18 | 2,32 | Microsoft Phi-4 Multimodal, quantization Q4_K_M |
| phi4-mm-vision-q8.gguf | 2026-09-29 | 2026-07-18 | 0,57 | Module vision Phi-4, quantization Q8 |
| q36-27b-nvfp4.gguf | 2026-10-01 | 2026-08-07 | 23,73 | Qwen 3.6 27B NVFP4, quantization NVIDIA FP4 |
| qwen2.5-1.5b-instruct-q4_k_m.gguf | 2026-09-22 | 2026-07-17 | 1,04 | Qwen 2.5 1.5B Instruct, quantization Q4_K_M |
| Qwen3.5-27B-Q3_K_M.gguf | 2026-09-22 | 2026-07-17 | 12,58 | Qwen 3.5 27B, quantization Q3_K_M |
| Qwen3.5-9B-Q4_K_M.gguf | 2026-09-22 | 2026-07-16 | 5,29 | Qwen 3.5 9B, quantization Q4_K_M |
| Qwen3.6-27B-NVFP4-MTP-GGUF.gguf | 2026-10-01 | 2026-08-07 | 15,08 | Qwen 3.6 27B NVFP4 Multi-Token Prediction, NVIDIA FP4 |
| Qwen3.6-27B-Q3_K_M.gguf | 2026-09-22 | 2026-07-17 | 12,65 | Qwen 3.6 27B, quantization Q3_K_M |
| Qwen3.6-27B-Q4_K_M.gguf | 2026-09-22 | 2026-07-16 | 15,66 | Qwen 3.6 27B, quantization Q4_K_M |
| Qwen3.6-35B-A3B-NVFP4-nvidia.gguf | 2026-10-01 | 2026-08-07 | 22,21 | Qwen 3.6 35B Actif 3B NVFP4, quantization NVIDIA FP4 |
| Qwen3.6-35B-A3B-UD-Q4_K_M.gguf | 2026-09-22 | 2026-07-16 | 20,61 | Qwen 3.6 35B Actif 3B Ultra Dense, quantization Q4_K_M |
| Unsloth-Qwen3.6-27B-NVFP4-Q8.gguf | 2026-10-01 | 2026-08-07 | 21,58 | Qwen 3.6 27B NVFP4 optimisé Unsloth, quantization Q8 |