Loading…
Loading…
Models / Kimi-Dev
GPU memory needed (smallest version of each): Kimi-Dev 72B about 166.8 GB. The cheapest runs on 8x RTX 3090 from $2.25/h right now.
1 model (72B) · ↓ 2.4K downloads a month · from $2.25/h on 8x RTX 3090 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-Dev-72B | vLLM | 145 GB | 166.8 GB | $2.25/h 8x RTX 3090 |
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").