Mistral
Mixtral 8x22B
当前
29.2K下载量752点赞Apr 2024发布日期66K tokens上下文Apache 2.0许可证34 基础质量
Mixtral 8x22B (141B parameters) requires approximately 90.9 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 39B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 105 GB of VRAM.
快速开始
— 复制粘贴即可本地运行Copy-paste commands to run Mixtral 8x22B on your machine.
Run
ollama run mixtral:8x22bQuick specs
Parameters141B (39B active)
Architecturemoe (MoE)
Context66K tokens
Modalitytext
Min RAM55 GB
Rec. RAM86 GB (Q4_K_M)
LicenseApache 2.0
FamilyMixtral
✓ Chat✓ Reasoning
About this model
- •[AVAILABLE_TOOLS]
- •[/AVAILABLE_TOOLS]
相关模型
快速推荐
最佳硬件
Mixtral 8x22B 的最佳选择
运行此模型
量化选项
各量化级别的 VRAM 估算
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 55.0 GB | Low | — |
Q3_K_S | 3 | 69.1 GB | Low | — |
NVFP4 | 4 | 79.0 GB | Medium | — |
Q4_K_M | 4 | 86.0 GB | Medium | — |
Q5_K_M | 5 | 101.5 GB | High | — |
Q6_K | 6 | 115.6 GB | High | — |
Q8_0 | 8 | 150.9 GB | Very High | — |
F16 | 16 | 289.0 GB | Maximum | — |
Quality benchmarks
Mixtral 8x22B benchmark scores
Coding
SWE-bench Verified—
HumanEval+78.6%
Aider Polyglot—
LiveCodeBench—
Reasoning
MMLU-Pro38.7%
GPQA Diamond16.4%
MATH-50018.7%
ARC Challenge—
General
Chatbot Arena—
IFEval71.8%
Source: official · 2024-04-16
硬件兼容性
全部硬件的适配估算
Computing compatibility...
内存详细分析
Reference: RTX 2060 6GB
Weights86.0 GB
KV Cache3.4 GB
Runtime0.9 GB
Headroom0.6 GB
常见问题
FAQ — Mixtral 8x22B
另请参阅