MiniMax Models — Hardware Requirements

7 MiniMax models from MiniMaxAI and the community, from the smallest that runs in 63.5 GB of VRAM up to 456.1B parameters. Every row links to full quantization tables and GPU compatibility.

All MiniMax Models by Size

ModelParamsContext
MiniMax M2.7 BF16 Ultra Uncensored Heretic228.7B205K
MiniMax M2.7228.7B205K
MiniMax M2.5228.7B197K
MiniMax M2.1228.7B197K
MiniMax M2228.7B197K
MiniMax Text 01456.1B10240K
MiniMax M1 80k456.1B10240K

How MiniMax Compares — Benchmark Rating

MiniMax M2.7 is the highest-rated MiniMax model with an overall benchmark rating of 68.4/100 — #5 among 75 open models. The top proprietary model, GPT 5.5, scores 88.8. Click a model to see its full benchmark breakdown.

GPT 5.5 · proprietary88.8
Claude Opus 4.7 · proprietary87.6
Claude Fable 5 · proprietary86.6
GPT 5.4 · proprietary86.6
Claude Opus 4.8 · proprietary84.4
Composite of normalized public benchmark scores (methodology) · MiniMax · other models

Frequently Asked Questions

How much VRAM do I need to run a MiniMax model?
The smallest MiniMax model, MiniMax M2.7, runs from 63.5 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which MiniMax models can I run on a 16 GB GPU?
No MiniMax model currently fits in 16 GB of VRAM — the family starts at 63.5 GB.
What is the most popular MiniMax model to run locally?
MiniMax M2.7 is the most downloaded MiniMax model in local-friendly quantized formats. It runs from 63.5 GB of VRAM.
How do MiniMax models score on benchmarks?
MiniMax M2.7 leads the family with an overall benchmark rating of 68.4/100, ranking #5 among 75 open models, while the top proprietary model, GPT 5.5, scores 88.8. See the comparison chart above for the full standings.