Run Mixtral 8x22B Instruct locally

Mixtral 8x22B Instruct is 141B parameters (39B active per token — a mixture-of-experts, so it still needs room for all 141B in memory). Here's the VRAM it needs at each quantization, the smallest GPU that fits, and how a self-hosted box compares with the cheapest verified API.

VRAM by quantization

QuantizationVRAM neededFits onNotes
int4 (Q4)84.6 GB2× H100 (160 GB) ($3.98/hr)smallest footprint, minor quality loss
int8 (Q8)169.2 GB4× H100 (320 GB) ($7.96/hr)near-lossless
fp16 (full)338.4 GB8× H100 (640 GB) ($15.92/hr)reference quality

VRAM ≈ params × bytes/param × 1.2 (overhead). See the fullmethod and break-even calculator.

Self-host vs API

Cheapest API for Mixtral 8x22B Instruct is $8 / 1M tokens(blended) via Mistral AI. Running it yourself in int4 fits a2× H100 (160 GB) at $3.98/hr — about $2,905.4/month at 24/7. Those two lines cross at roughly 363M tokens/month: below that the API wins on cost, above it the dedicated GPU does (assuming you keep it busy). Tune your own volume in the break-even calculator.

Run it at home

No cloud account needed: Mixtral 8x22B Instruct in int4 (84.6 GB) fits a Mac Studio M5 Ultra (96 GB unified), a $5,499 one-off buy. Amortized over 3 years that's about $0.2092/hr — hardware only, electricity aside. Against the Mistral AI API at $8/1M, buying it pays for itself after roughly 687M tokens total. Below that the API is cheaper; a machine that mostly sits idle rarely earns back its price.

Get the weights

Quantized builds on the model hubs — links search live, so they track new builds as they appear: