Best Local Cohere Models
The best local Cohere model is Command A (22.5 intelligence) — open weights on Hugging Face, small enough to run on your own hardware. North Mini Code (free) (19.8) is next.
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.
- 1
command-aJSON22.5 intel · $2.50/M · 256K ctx22.5Intelligence - 2north-mini-code:freeReasoningTools19.8 intel · Free/M · 256K ctx19.8Intelligence
Frequently asked
What is the best local Cohere model?
The best local Cohere model is Command A (22.5 intelligence) — open weights on Hugging Face, small enough to run on your own hardware. North Mini Code (free) (19.8) is next.
What's a good alternative to Command A?
North Mini Code (free) (19.8) is the closest alternative on this metric. See the full ranking above for the tradeoffs.
How many Cohere models are there?
modelgrep tracks 5 Cohere models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Command A. 2 of them qualify for this ranking.