Qwen/QwQ-32B

Text Generation • Updated 4 days ago • 335k • • 2.22k

Note Best local model for debugging and solving problems. Smarter than ~70-120B models. https://docs.unsloth.ai/basics/tutorial-how-to-run-qwq-32b-effectively

meta-llama/Llama-3.3-70B-Instruct

Text Generation • Updated Dec 21, 2024 • 898k • • 2.14k

Note Jack of all trades, master of none. I can run locally.

deepseek-ai/DeepSeek-R1

Text Generation • Updated 20 days ago • 2.29M • • 11.3k

Note Most powerful open model. Best FIM model. I rely on inference providers to run it.

nbeerbower/mistral-nemo-gutenberg-12B-v4

Text Generation • Updated Sep 6, 2024 • 138 • 20

Note Best creative writing model I've used. Very fast.

HuggingFaceTB/SmolLM2-360M-Instruct

Text Generation • Updated 24 days ago • 77.9k • • 102

Note My favorite model for cramped spaces. I can even run this on my old Windows XP laptop with 1G RAM. A fun toy, but not good for much.

deepseek-ai/DeepSeek-Coder-V2-Lite-Base

Text Generation • Updated Jul 3, 2024 • 229k • 75

Note FIM only, very fast.

Qwen/Qwen2.5-Coder-7B

Text Generation • Updated Nov 18, 2024 • 66.7k • • 97

Note FIM only, very fast.

Qwen/Qwen2.5-Coder-32B

Text Generation • Updated Nov 18, 2024 • 7.88k • 109

Note FIM only.