Mixtral 8x22B Instruct
The bigger Mixtral. 141B total / 39B active. Strong general model, workstation-tier deployment.
Positioning
Mixtral 8x22B is the heavyweight Mixtral release — 141B total parameters, 39B active per token. Closer to a real flagship than 8x7B was, but the disk and memory footprint pushes it past consumer rigs into workstation territory. Largely superseded by Llama 4 Scout for the same hardware tier.
Strengths
- Apache 2.0 license — license-clean alternative to Llama 4 in the workstation-class MoE space.
- 39B active per token keeps tok/s competitive with dense ~40B models.
- Strong multilingual — Mistral's European focus carries through.
Limitations
- Workstation hardware required — 84 GB at Q4_K_M, partial-offload only on 24 GB cards.
- Quality has been overtaken by Llama 4 Scout and DeepSeek V3 for similar memory.
- Long context is weaker than the spec implies — recall degrades past 24K.
Real-world performance on RTX 4090
- Q4_K_M (84 GB) — heavy offload: 7–12 tok/s, ~64 GB+ system RAM required
- Q5_K_M (97 GB) — workstation only
- Q8_0 (141 GB) — multi-card workstation
Should you run this locally?
Yes, for workstation rigs where Apache-license MoE matters more than absolute capability — and for legacy Mixtral fine-tunes already in use. No, for new deployments — Llama 4 Scout or DeepSeek V3 are the better picks at similar hardware investment.
How it compares
- vs Llama 4 Scout → similar memory footprint; Scout wins on multimodality + architecture sophistication. New work tilts toward Scout.
- vs Mixtral 8x7B → 8x22B is a legitimate flagship where 8x7B was a tech demo. If MoE is the goal, 8x22B is the only Mixtral worth running today.
- vs DeepSeek V3 → V3 has more total params but very strong active-param efficiency; V3 wins on quality, Mixtral 8x22B wins on license clarity.
Run this yourself
ollama pull mixtral:8x22b-instruct-v0.1-q4_K_M
ollama run mixtral:8x22b-instruct-v0.1-q4_K_M
›Why this rating
7.5/10 — the more credible MoE option in the Mixtral family, but at 141B total / 39B active it's workstation-only and now eclipsed by Llama 4 Scout (similar size, native multimodal) and DeepSeek V3 (fewer active params, better quality). Loses points for being out of the consumer-card zone.
Overview
The bigger Mixtral. 141B total / 39B active. Strong general model, workstation-tier deployment.
Featured in this stack
The L3 execution stacks that pick this model as a recommended component, with the one-line note explaining the role it plays in each.
- Stack · L3·Homelab tier·Role: Large MoE model (39B-active, 141B total)Quad RTX 3090 workstation stack — the prosumer 100B-class ceiling
Mixtral 8x22B at AWQ-INT4 fits across 88 GB effective with comfortable headroom. Expert routing across 4 cards is bandwidth-friendlier than dense tensor-parallel — the no-NVLink penalty between paired cards shrinks for MoE.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- Apache 2.0
- Multilingual
Weaknesses
- 96GB+ VRAM required
- Outpaced by Qwen 3 235B-A22B
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 84.0 GB | 96 GB |
Get the model
Ollama
One-line install
ollama run mixtral:8x22bRead our Ollama review →HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Mixtral 8x22B Instruct.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run Mixtral 8x22B Instruct?
Can I use Mixtral 8x22B Instruct commercially?
What's the context length of Mixtral 8x22B Instruct?
How do I install Mixtral 8x22B Instruct with Ollama?
Source: huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Mixtral 8x22B Instruct runs on your specific hardware before committing money.