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

MiMo-V2.5-Pro

by XiaomiMiMo

1023B params · text-generation · 661 likes · 102.3k downloads

MiMo-V2.5-Pro is a 1023B parameter model. At Q4 quantization it requires 512GB of VRAM. It requires a GPU with at least 512GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
deepinfra78 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0