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

Mixtral-8x22B-Instruct-v0.1

by mistralai

141B params · 746 likes · 25.1k downloads

Mixtral-8x22B-Instruct-v0.1 is a 141B parameter model. At Q4 quantization it requires 70GB of VRAM. It runs comfortably on H200 SXM 141 GB (50 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
Nscale19 tok/s

GPU compatibility

GPUVRAMQ4 DecodeVerdict
M4 Max 128GB128GB3 tok/stight
H200 SXM 141 GB141GB50 tok/scomfortable
M2 Ultra 192GB192GB4 tok/stight
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0