New in llama.cpp: Decision Models
• 93
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
GGUF decision models for the /v1/systemone API in llama.cpp
-
ggml-org/Clef-GGUF
Image-Text-to-Text • 27B • Updated • 17.2k • 23 -
ggml-org/Clef-Flash-GGUF
Image-Text-to-Text • 9B • Updated • 40.8k • 33 -
ggml-org/OpenJev-GGUF
Image-Text-to-Text • 27B • Updated • 8.18k • 19 -
ggml-org/Laya-GGUF
Text Classification • 0.4B • Updated • 13.5k • 30
Collection for Nemotron-Nano-3-30B-A3B models
Collection for Nemotron-3-Super-120B models
-
ggml-org/gemma-4-E2B-it-GGUF
Any-to-Any • 5B • Updated • 59.7k • 90 -
ggml-org/gemma-4-E4B-it-GGUF
Any-to-Any • 8B • Updated • 478k • 95 -
ggml-org/gemma-4-12B-it-GGUF
Any-to-Any • 12B • Updated • 52.5k • 93 -
ggml-org/gemma-4-26B-A4B-it-GGUF
Image-Text-to-Text • 25B • Updated • 324k • 92
Collection for Devstral-Small-2-24B-Instruct-2512 models
Adapters extracted from fine tuned models, using mergekit-extract-lora
-
ggml-org/LoRA-Llama-3-Instruct-abliteration-8B-F16-GGUF
88.1M • Updated • 74 • 1 -
ggml-org/LoRA-Qwen2.5-1.5B-Instruct-abliterated-F16-GGUF
93.6M • Updated • 130 • 5 -
ggml-org/LoRA-Qwen2.5-3B-Instruct-abliterated-F16-GGUF
0.1B • Updated • 90 • 1 -
ggml-org/LoRA-Qwen2.5-7B-Instruct-abliterated-v3-F16-GGUF
90.9M • Updated • 55 • 4
Models that are used for presets in llama.cpp.
Collection of models for Gemma 3-270m
Vision and audio models compatible with llama-server and llama-mtmd-cli
-
ggml-org/Ministral-3-3B-Reasoning-2512-GGUF
Image-Text-to-Text • 3B • Updated • 905 • 2 -
ggml-org/Ministral-3-8B-Reasoning-2512-GGUF
Image-Text-to-Text • 8B • Updated • 1.26k • 2 -
ggml-org/Ministral-3-14B-Reasoning-2512-GGUF
Image-Text-to-Text • 14B • Updated • 1.09k • 3 -
ggml-org/Ministral-3-3B-Instruct-2512-GGUF
Image-Text-to-Text • 3B • Updated • 1.08k • 4
-
ggml-org/SmolVLM2-2.2B-Instruct-GGUF
2B • Updated • 37.1k • 42 -
ggml-org/SmolVLM2-500M-Video-Instruct-GGUF
0.4B • Updated • 14k • 20 -
ggml-org/SmolVLM2-256M-Video-Instruct-GGUF
Image-Text-to-Text • 0.2B • Updated • 5.6k • 13 -
ggml-org/SmolVLM-Instruct-GGUF
2B • Updated • 3.34k • 9
Recommended models for the llama.vim and llama.vscode plugins
-
ggml-org/Qwen2.5-Coder-0.5B-Q8_0-GGUF
Text Generation • 0.5B • Updated • 797 • 11 -
ggml-org/Qwen2.5-Coder-1.5B-Q8_0-GGUF
Text Generation • 2B • Updated • 5.76k • 23 -
ggml-org/Qwen2.5-Coder-3B-Q8_0-GGUF
Text Generation • 3B • Updated • 2.03k • 17 -
ggml-org/Qwen2.5-Coder-7B-Q8_0-GGUF
Text Generation • 8B • Updated • 2.41k • 13
Voice Activity Detection (VAD) models for whisper.cpp.
GGUF decision models for the /v1/systemone API in llama.cpp
-
ggml-org/Clef-GGUF
Image-Text-to-Text • 27B • Updated • 17.2k • 23 -
ggml-org/Clef-Flash-GGUF
Image-Text-to-Text • 9B • Updated • 40.8k • 33 -
ggml-org/OpenJev-GGUF
Image-Text-to-Text • 27B • Updated • 8.18k • 19 -
ggml-org/Laya-GGUF
Text Classification • 0.4B • Updated • 13.5k • 30
Collection for Nemotron-Nano-3-30B-A3B models
Collection for Nemotron-3-Super-120B models
-
ggml-org/gemma-4-E2B-it-GGUF
Any-to-Any • 5B • Updated • 59.7k • 90 -
ggml-org/gemma-4-E4B-it-GGUF
Any-to-Any • 8B • Updated • 478k • 95 -
ggml-org/gemma-4-12B-it-GGUF
Any-to-Any • 12B • Updated • 52.5k • 93 -
ggml-org/gemma-4-26B-A4B-it-GGUF
Image-Text-to-Text • 25B • Updated • 324k • 92
Collection of models for Gemma 3-270m
Collection for Devstral-Small-2-24B-Instruct-2512 models
Vision and audio models compatible with llama-server and llama-mtmd-cli
-
ggml-org/Ministral-3-3B-Reasoning-2512-GGUF
Image-Text-to-Text • 3B • Updated • 905 • 2 -
ggml-org/Ministral-3-8B-Reasoning-2512-GGUF
Image-Text-to-Text • 8B • Updated • 1.26k • 2 -
ggml-org/Ministral-3-14B-Reasoning-2512-GGUF
Image-Text-to-Text • 14B • Updated • 1.09k • 3 -
ggml-org/Ministral-3-3B-Instruct-2512-GGUF
Image-Text-to-Text • 3B • Updated • 1.08k • 4
-
ggml-org/SmolVLM2-2.2B-Instruct-GGUF
2B • Updated • 37.1k • 42 -
ggml-org/SmolVLM2-500M-Video-Instruct-GGUF
0.4B • Updated • 14k • 20 -
ggml-org/SmolVLM2-256M-Video-Instruct-GGUF
Image-Text-to-Text • 0.2B • Updated • 5.6k • 13 -
ggml-org/SmolVLM-Instruct-GGUF
2B • Updated • 3.34k • 9
Adapters extracted from fine tuned models, using mergekit-extract-lora
-
ggml-org/LoRA-Llama-3-Instruct-abliteration-8B-F16-GGUF
88.1M • Updated • 74 • 1 -
ggml-org/LoRA-Qwen2.5-1.5B-Instruct-abliterated-F16-GGUF
93.6M • Updated • 130 • 5 -
ggml-org/LoRA-Qwen2.5-3B-Instruct-abliterated-F16-GGUF
0.1B • Updated • 90 • 1 -
ggml-org/LoRA-Qwen2.5-7B-Instruct-abliterated-v3-F16-GGUF
90.9M • Updated • 55 • 4
Recommended models for the llama.vim and llama.vscode plugins
-
ggml-org/Qwen2.5-Coder-0.5B-Q8_0-GGUF
Text Generation • 0.5B • Updated • 797 • 11 -
ggml-org/Qwen2.5-Coder-1.5B-Q8_0-GGUF
Text Generation • 2B • Updated • 5.76k • 23 -
ggml-org/Qwen2.5-Coder-3B-Q8_0-GGUF
Text Generation • 3B • Updated • 2.03k • 17 -
ggml-org/Qwen2.5-Coder-7B-Q8_0-GGUF
Text Generation • 8B • Updated • 2.41k • 13
Models that are used for presets in llama.cpp.
Voice Activity Detection (VAD) models for whisper.cpp.