Can MiniMax M3.1 Flash run on the A100 40GB?
Not fully in VRAM. Even at 2-bit with 8K context, MiniMax M3.1 Flash needs about 78.7 GB, more than the 38.0 GB usable on the A100 40GB. It can still run with offload (slower): Q4_K_M with part of the model in system RAM. Details and command.
Runs with offload (slower)
Runs with offload 4-bit (Q4_K_M) at 8K context: all attention layers plus the experts of 15 of 57 MoE layers on the A100 40GB (about 35.8 GB), and the experts of the other 42 layers in system RAM (about 90.6 GB). Needs a PC with at least 128 GB of system RAM. Speed is not estimated for this model (its active-parameter count is uncertain).
llama-server -m minimax-m3-1-flash-Q4_K_M.gguf -c 8192 -ngl 999 --n-cpu-moe 45
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) | 78.3 GB No | 78.7 GB No | 81.5 GB No | 92.8 GB No | — |
| 3-bit (Q3_K_M) | 102 GB No | 102 GB No | 105 GB No | 116 GB No | — |
| 4-bit (Q4_K_M) | 127 GB No | 127 GB No | 130 GB No | 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 (1555 GB/s), not a benchmark. Methodology.
Hardware that does fit it
RTX PRO 6000 BlackwellDGX SparkRyzen AI Max+ 395 128GBMac M3 Max 128GBMac M4 Max 128GBH200
What fits instead
- Cheapest listed GPU that runs MiniMax M3.1 Flash: DGX Spark (128 GB, launch MSRP $3,999) at Q2_K, fully in VRAM at 8K context.
- Largest popular model that fits the A100 40GB: Qwen3.6 35B A3B (36B, MoE) at Q6_K, about 29.9 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 M3.1 Flash on every GPU and Mac · Every model that runs on the A100 40GB · Other models that fit 48 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-M3.1-Flash), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.