unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 37.2k • 390
Smol Models
My favorite smaller models under 10B parameters.
-
-
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 56.9k • • 222 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • Updated • 2.08M • • 855 -
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 1.8M • • 688 -
Qwen/Qwen2.5-7B-Instruct
Text Generation • 8B • Updated • 12.5M • • 1.22k -
VIDraft/Gemma-3-R1984-4B
Image-Text-to-Text • 4B • Updated • 13 • 21 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 9.26M • • 5.73k -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 4.28M • 2.1k -
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 129k • 1.29k -
microsoft/Phi-4-mini-reasoning
Text Generation • Updated • 31.8k • 223 -
microsoft/bitnet-b1.58-2B-4T
Text Generation • 0.8B • Updated • 15.5k • 1.43k -
microsoft/bitnet-b1.58-2B-4T-gguf
Text Generation • 2B • Updated • 70.4k • 266 -
unsloth/Qwen3-4B-Thinking-2507-GGUF
4B • Updated • 4.83k • 97 -
nvidia/NVIDIA-Nemotron-Nano-9B-v2
Text Generation • 9B • Updated • 525k • 488