Can MiniMax Text 01 run on the H100 SXM?
Not fully in VRAM. Even at 2-bit with 8K context, MiniMax Text 01 needs about 163 GB, more than the 76.0 GB usable on the H100 SXM. It can still run with offload (slower): Q2_K with part of the model in system RAM, about 3.9–7.9 tokens/sec (estimate). Details and command.
Runs with offload (slower)
Runs with offload 2-bit (Q2_K) at 8K context: all attention layers plus the experts of 34 of 80 MoE layers on the H100 SXM (about 74.5 GB), and the experts of the other 46 layers in system RAM (about 87.3 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 3.9–7.9 tokens/sec (slow but usable), versus a bandwidth ceiling of ~185 tok/s if it fit fully in VRAM.
llama-server -m minimax-text-01-Q2_K.gguf -c 8192 -ngl 999 --n-cpu-moe 46
Estimate, not a benchmark. No GGUF repo was found on Hugging Face yet; point -m at your own GGUF file. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, raise --n-cpu-moe by 1-2; if VRAM is left over, lower it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 161 GB No | 163 GB No | 170 GB No | 200 GB No | — |
| 3-bit (Q3_K_M) | 210 GB No | 211 GB No | 218 GB No | 248 GB No | — |
| 4-bit (Q4_K_M) | 262 GB No | 263 GB No | 270 GB No | 300 GB No | — |
| 5-bit (Q5_K_M) | 305 GB No | 306 GB No | 313 GB No | 343 GB No | — |
| 6-bit (Q6_K) | 350 GB No | 352 GB No | 359 GB No | 389 GB No | — |
| 8-bit (Q8_0) | 453 GB No | 455 GB No | 462 GB No | 492 GB No | — |
| 16-bit (F16/BF16) | 852 GB No | 853 GB No | 860 GB No | 890 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (3350 GB/s), not a benchmark. Methodology.
Hardware that does fit it
Mac M3 Ultra 256GBMac M3 Ultra 512GB
What fits instead
- No listed GPU with a list price runs MiniMax Text 01 fully in memory. The smallest listed hardware that does is the Mac M3 Ultra 256GB (256 GB).
- Largest popular model that fits the H100 SXM: gpt-oss 120B (117B, MoE) at F16, about 61.9 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
MiniMax Text 01 on every GPU and Mac · Every model that runs on the H100 SXM · Other models that fit 64 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (MiniMaxAI/MiniMax-Text-01), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.