Loading…
Loading…
Models / MiMo-V2.6-Flash-RL
1 model (~311B) · ↓ 117.9K downloads a month · from $4.71/h on 8x RTX 5090 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 |
|---|---|---|---|---|
| OriginalXiaomiMiMo/MiMo-V2.6-Flash-RL | vLLM | 173 GB | 195.7 GB | $4.71/h 8x RTX 5090 |
| NVFP4 (ProCreations)ProCreations/MiMo-V2.6-Flash-RL-NVFP4 | vLLM | 194 GB | 219.1 GB | $4.71/h 8x RTX 5090 |
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").