Best Local MoonshotAI Models
The best local MoonshotAI model is Kimi K2.6 (44.2 intelligence) — open weights on Hugging Face, small enough to run on your own hardware. Kimi K2.7 Code (41.9) and Kimi K2.5 (35.4) 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.
- 1
kimi-k2.6ReasoningToolsJSON+144.2 intel · $0.684/M · 262K ctx44.2Intelligence - 2kimi-k2.7-codeReasoningToolsJSON+141.9 intel · $0.710/M · 262K ctx41.9Intelligence
- 3kimi-k2.5ReasoningToolsJSON+135.4 intel · $0.570/M · 262K ctx35.4Intelligence
- 4kimi-k2-thinkingReasoningToolsJSON32.7 intel · $0.600/M · 262K ctx32.7Intelligence
- 5kimi-k2-0905ToolsJSON23.5 intel · $0.600/M · 262K ctx23.5Intelligence
- 6kimi-k2Tools19.4 intel · $0.570/M · 131K ctx19.4Intelligence
Frequently asked
What is the best local MoonshotAI model?
The best local MoonshotAI model is Kimi K2.6 (44.2 intelligence) — open weights on Hugging Face, small enough to run on your own hardware. Kimi K2.7 Code (41.9) and Kimi K2.5 (35.4) round out the top three.
What's a good alternative to Kimi K2.6?
Kimi K2.7 Code (41.9) is the closest alternative on this metric, followed by Kimi K2.5 (35.4). See the full ranking above for the tradeoffs.
How many MoonshotAI models are there?
modelgrep tracks 7 MoonshotAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Kimi K3. 6 of them qualify for this ranking.