Will this model run on your hardware?
Can I run MoonshotAI: Kimi K2 Thinking locally?
- 1026B parameters (72B active, MoE)
- context up to 256K
- licence: other
- Weights: moonshotai/Kimi-K2-Thinking · GGUF: unsloth/Kimi-K2-Thinking-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 1091.1 GB |
| Q6_K | 842.9 GB |
| Q5_K_M | 728.7 GB |
| Q4_K_M | 621.2 GB |
| Q3_K_M | 490.0 GB |
| Q2_K | 374.1 GB |
Run it locally
ollama run hf.co/unsloth/Kimi-K2-Thinking-GGUF:Q4_K_M
llama serve -hf unsloth/Kimi-K2-Thinking-GGUF:Q4_K_M
LM Studio: open unsloth/Kimi-K2-Thinking-GGUF