CanItRun Logocanitrun.

MiniMax M2.7 229B

MiniMax M2.7 229B needs roughly 130.6GB VRAM at Q4_K_M quantization (515.3GB at FP16). 14 GPUs we track can run it fully in VRAM at 8k context.

MiniMax229B params10B active (MoE)200k contextMiniMaxCommercial use ok

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP16458.0 GB2.08 GB515.3 GB
Q8229.0 GB2.08 GB258.8 GB
Q6_K171.8 GB2.08 GB194.7 GB
Q5_K_M143.1 GB2.08 GB162.6 GB
Q4_K_M114.5 GB2.08 GB130.6 GB
Q3_K_M91.6 GB2.08 GB104.9 GB
Q2_K68.7 GB2.08 GB79.3 GB

Benchmarks

Benchmarks for this model are not yet available on the Open LLM Leaderboard v2. This is common for recently released models. Check back soon.

GPUs that run MiniMax M2.7 229B natively (14)

Plus 2 GPUs that run it with CPU offload (slower)

Notes

Successor to M2.5 with self-evolving RL capabilities. Highest open-weight GDPval-AA Elo (1495).

Hugging Face ↗Released 2026-03-18