Tok/s vs cost of self-hosting XiaomiMiMo/MiMo-V2.6-Flash-RL on H200:8.
Run it yourself
mimo-v2.6-flash@v2 · H200:8
$ iwant launch mimo-v2.6-flashResults
Dashed lines estimate the same throughput at another cloud's price for the same GPUs.
| setup | $/hour | peak tok/s | $/1M at peak | |
|---|---|---|---|---|
| mimo-v2.6-flash@v2 · GCP a3-ultragpu-8g H200:8 asia-south1-b Spot | $60.89 | 6,778 | $2.4954 | |
| mimo-v2.6-flash@v2 · AWS ap-northeast-2 spot (estimated) | $12.18 | 6,778 | $0.4993 | |
| mimo-v2.6-flash@v2 · AWS us-east-1 on-demand (estimated) | $63.30 | 6,778 | $2.5940 |