unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation
•
8B
•
Updated
•
110k
•
338
Smol Models
My favorite smaller models under 10B parameters.
-
-
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 18k • • 210 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • 8B • Updated • 695k • • 817 -
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 269k • • 552 -
Qwen/Qwen2.5-7B-Instruct
Text Generation • 8B • Updated • 8.17M • • 849 -
VIDraft/Gemma-3-R1984-4B
Image-Text-to-Text • 4B • Updated • 128 • 18 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 5.24M • • 4.85k -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 1.92M • • 1.79k -
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 106k • 1.26k -
microsoft/Phi-4-mini-reasoning
Text Generation • 4B • Updated • 16.4k • 211 -
microsoft/bitnet-b1.58-2B-4T
Text Generation • 0.8B • Updated • 11.3k • 1.21k -
microsoft/bitnet-b1.58-2B-4T-gguf
Text Generation • 2B • Updated • 5.13k • 211 -
unsloth/Qwen3-4B-Thinking-2507-GGUF
4B • Updated • 19.1k • 62 -
nvidia/NVIDIA-Nemotron-Nano-9B-v2
Text Generation • 9B • Updated • 190k • 419