Can MiniMax M3.1 Flash run on the H200?
Yes. At 8K context the best fit is Q3_K_M, using about 102 GB of the 134 GB usable on the H200.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 78.3 GB Fits | 78.7 GB Fits | 81.5 GB Fits | 92.8 GB Fits | — |
| 3-bit (Q3_K_M) | 102 GB Fits | 102 GB Fits | 105 GB Fits | 116 GB Fits | — |
| 4-bit (Q4_K_M) | 127 GB Tight | 127 GB Tight | 130 GB Tight | 141 GB No | — |
| 5-bit (Q5_K_M) | 148 GB No | 148 GB No | 151 GB No | 162 GB No | — |
| 6-bit (Q6_K) | 170 GB No | 170 GB No | 173 GB No | 184 GB No | — |
| 8-bit (Q8_0) | 219 GB No | 220 GB No | 223 GB No | 234 GB No | — |
| 16-bit (F16/BF16) | 412 GB No | 412 GB No | 415 GB No | 426 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.
More
MiniMax M3.1 Flash on every GPU and Mac · Every model that runs on the H200 · Other models that fit 64 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (MiniMaxAI/MiniMax-M3.1-Flash), NVIDIA specs. Data as of 2026-11-17.