BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

Mixtral 8x22B Instruct

By Mistral AI · France

chat general moe multilingual fr
Parameters
141B
License
Apache 2.0
Context
62k
VRAM (Q4)
82 GB
Released
April 2024

Overview

Mistral AI's mature 141B/39B-active MoE under Apache 2.0, scoring 77.8 on MMLU and 45.1 on HumanEval. A proven general-purpose workhorse at roughly 80GB in Q4.

When to pick this model

  • Stable, well-understood production deployments
  • Apache-licensed commercial products
  • Multilingual general chat including French
  • Workloads where reliability beats latest benchmarks
  • Teams with existing Mixtral infrastructure

VRAM requirements by quantization

QuantizationVRAM required
Q4_K_M (recommended)82 GB
Q5_K_M100 GB
Q8_0150 GB
FP16 (no quantization)282 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Published benchmark scores

BenchmarkScore
MMLU77.8
GSM8K78.6

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

  • Battle-tested mature MoE
  • Strong general-purpose performance
  • Apache 2.0 license
  • Solid multilingual coverage

Limitations

  • 80GB in Q4 still demands serious hardware
  • Coding trails newer specialists
  • 64K context lags 2026 competitors
  • Outclassed by newer Mistral releases on most benchmarks

Architecture & training

Architecture: Sparse MoE · 8 experts · 141B/39B active · GQA

Training: Apache 2.0, 64k ctx.

Verdict

Still a dependable Apache-licensed generalist, but newer Mistral models now beat it across the board.

Quick start

ollama run mixtral:8x22b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Tools

Is Mixtral 8x22B Instruct the right pick for you?

Compute self-hosted ROI → Back to catalog