What GPU do I need to run MiniMaxAI/MiniMax-M2.1?
228.7B parameters, published in F8_E4M3. View on Hugging Face
Set up MiniMax-M2.1MiniMax-M2.1 is published by MiniMaxAI on Hugging Face, with 32,739 downloads and 1,359 likes to date. It's a MiniMaxM2ForCausalLM model built for text-generation, published natively in F8_E4M3.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP8 (native) | 213.0 GB | 255.6 GB | RTX 4090 | 6 | $2.64/hr |
| INT4 (quantized) | 106.5 GB | 127.8 GB | RTX 5060 Ti | 8 | $0.880/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run MiniMax-M2.1 at its published (F8_E4M3) precision: 6× RTX 4090, at $0.441/hr per GPU ($2.64/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
MiniMax-M2.1: common questions
Can MiniMax-M2.1 run on a single GPU?
No. At FP8 (native) it needs 255.6 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 48.0 GB RTX 4090, and it takes 6 of them.
Is MiniMax-M2.1 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 255.6 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 127.8 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.
How many GPUs do I need to run MiniMax-M2.1?
6 at FP8 (native). It needs 255.6 GB of VRAM and the cheapest capable live offer is a 48.0 GB RTX 4090, so 6 of them come to $2.64/hr in total.
Does quantizing MiniMax-M2.1 lower the GPU bill?
Yes. At FP8 (native) the cheapest live fit is 6 RTX 4090 cards at $2.64/hr. At INT4 (quantized) it drops to 8 RTX 5060 Ti cards at $0.880/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More MiniMax M2 models
- MiniMax-M2.7 (228.7B, F8_E4M3)
- MiniMax-M2 (228.7B, F8_E4M3)
- MiniMax-M2.5 (228.7B, F8_E4M3)
Related reading: RTX 4090 pricing and specs, and The best GPUs for AI, ranked.
