Loading…
Loading…
Models / MiroThinker-1.7
GPU memory needed (smallest version of each): MiroThinker-1.7 ~235B about 526.4 GB. The cheapest runs on 4x Nvidia B200 from $39.67/h right now.
1 model (~235B) · ↓ 83 downloads a month · from $39.67/h on 4x Nvidia B200 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 |
|---|---|---|---|---|
| Originalmiromind-ai/MiroThinker-1.7 | vLLM | 470 GB | 526.4 GB | $39.67/h 4x Nvidia B200 |
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").