The best local LLM is MiniMax M3 (44.4 intelligence) — open weights on Hugging Face, small enough to run on your own hardware. DeepSeek V4 Pro (44.3) and Kimi K2.6 (44.2) round out the top three.
The best local LLMs — open-weight models small enough to run on your own hardware with Ollama, llama.cpp or vLLM — ranked by intelligence. Frontier-scale open models (400B+) are excluded: downloadable isn't the same as runnable. Every model here is on Hugging Face.
The best local LLM is MiniMax M3 (44.4 intelligence) — open weights on Hugging Face, small enough to run on your own hardware. DeepSeek V4 Pro (44.3) and Kimi K2.6 (44.2) round out the top three.
The best local AI model is MiniMax M3 (44.4 intelligence) — open weights on Hugging Face, small enough to run on your own hardware. DeepSeek V4 Pro (44.3) and Kimi K2.6 (44.2) round out the top three.
DeepSeek V4 Pro (44.3) is the closest alternative on this metric, followed by Kimi K2.6 (44.2). See the full ranking above for the tradeoffs.