what/llm/can/i/run

models/mistralai-mixtral-8x22b-instruct-v0.1

Mixtral 8x22b v0.1

Sources arena, livebench · Confidence B

params

141B

MoE total

bench sources

2

mid conf

context

—

max tokens

license

Apache 2.0

permissive

▸Model meta

canonical: mistralai/Mixtral-8x22B-Instruct-v0.1
parameters: 141B
organization: Mistral
license: Apache 2.0
context: —
downloads: —

▸Benchmark breakdown

LiveBench

coding20.0

overall20.0

▸Hardware fit matrix

by gpu tier	Q2_K 52.9 GB	Q4_K_M 70.5 GB	Q5_K_M 88.1 GB	Q6_K 105.8 GB	Q8_0 141.0 GB	FP16 282.0 GB
8 GB tier rtx 3050 · 4060
12 GB tier rtx 3060 · 4070
16 GB tier rtx 4080 · 4060 ti 16g
24 GB tier rtx 3090 · 4090
32 GB tier rtx 5090 · m3 max
48 GB tier a6000 · m3 max 64
80 GB tier h100 · m3 ultra 128	GREAT 35 t/s	OK 26 t/s

full fit · production speed tight fit · usabledoesn't fit

Get personalized ranking

Tell us your machine — we'll tell you if this is actually your best pick, or what's better.

Rank for my hardware