vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

MiniMax-M3

by MiniMaxAI

427B params · image-text-to-text · 1.2k likes · 104.1k downloads

MiniMax-M3 is a 427B parameter model. At Q4 quantization it requires 214GB of VRAM. It requires a GPU with at least 214GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
Novita39 tok/s
Together AI19 tok/s
Fireworks95 tok/s
Featherless
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0