Mixtral 8x22B
Mixtral 8x22B is an open-weights language model from Mistral, released April 17, 2024. It has 141B parameters (dense). On the Epoch Capabilities Index it scores 118.7, rank 188 of 256 rated models.
Check it against your own PC →
Can you run Mixtral 8x22B locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 23.2 GB | 18.0 GB | ~2 |
| 32 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 31.2 GB | 10.0 GB | ~3 |
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Knowledge | 27.8 | GPQA diamond, MMLU |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 70.4% |
| MATH level 5 | 24.2% |
| GPQA Diamond | 12.6% |
Links
Models with a similar score
Qwen2-72B · GPT-4 (Mar 2023) · Llama 3-70B · DeepSeek-V2 (MoE-236B, May 2024) · Gemini 1.5 Flash (May 2024) · GPT-4 (Jun 2023) · Mistral Large · Claude 3 Sonnet
More from Mistral
Mistral Large 4 · Mistral Large 4 Preview · Mistral Large 4 1T A52B · Leanstral 1.5 · Mistral Medium 3.5 · Mistral Small 4 · Devstral Small 2 · Devstral 2