Can I run MiniMax-M2.5 on an NVIDIA B200?
Probably, at 4-bit
The published weights are too big, but a 4-bit version (about 129 GB) would fit, with room for ≈ 128K tokens of context. The site hasn't analyzed a GGUF of MiniMax-M2.5 yet.
Files and context on NVIDIA B200
Each file of MiniMax-M2.5 (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On NVIDIA B200 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 230 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 129 GB | Fits | 128K | 192K |