How to run Mixtral 8x7B Instruct locally

Mixtral 8x7B Instruct (Mistral AI, 46.7B) runs on your own machine for $0 if you have about 34 GB of VRAM. Here's how to run it with Ollama, LM Studio, or llama.cpp — and what it would cost the other ways.

VRAM to run

~34 GB

Download

~26 GB

Quant

Q4_K_M

Context

32.8K

Three ways to run Mixtral 8x7B Instruct locally

1. Ollama — the one-liner

Auto-downloads a 4-bit quant and starts a chat — the simplest option.

ollama run mixtral:8x7b

First run downloads ~26 GB, then it's offline and free. Get Ollama at ollama.com.

2. LM Studio — point-and-click

Open LM Studio, search “Mixtral 8x7B Instruct”, and download a quant that fits your VRAM (≈34 GB at Q4_K_M). Load it and chat — fully offline. It also serves a local OpenAI-compatible API you can point Spanvero at.

3. llama.cpp — maximum control

Grab a community GGUF build of Mixtral 8x7B Instruct from Hugging Face (search “Mixtral 8x7B Instruct GGUF” — bartowski and unsloth publish reliable ones), then run:

./llama-cli -m <Q4_K_M-file>.gguf -p "Hello" -ngl 99

Or serve it with ./llama-server -m <file>.gguf for an OpenAI-compatible API on :8080.

What it costs — $0 markup

On your machine: $0 — you already have the hardware (needs ~34 GB VRAM).
No GPU big enough? Use your own API key at about $0.24/1M tokens (last-known), or rent a GPU by the hour. Full cost breakdown →

License: commercial use OK.

Browse: Mixtral 8x7B Instruct cost · models for your GPU · all models

Open the free Spanvero advisor → — it detects your hardware and confirms what fits.