Loading…
Loading…
Models / Kimi-K2-Thinking
1 model (~1.03e+03B) · ↓ 279.8K downloads a month · from $11.77/h on 8x RTX PRO 6000 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalmoonshotai/Kimi-K2-Thinking | vLLM | 594 GB | 678.4 GB | $11.77/h 8x RTX PRO 6000 |
| NVFP4 (nvidia)nvidia/Kimi-K2-Thinking-NVFP4 | vLLM | 594 GB | 678.4 GB | $11.77/h 8x RTX PRO 6000 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").