Mistral
Mistral Small 4 119B
前沿
52.6K下载量380点赞Jan 2026发布日期256K tokens上下文Mistral Research License许可证94 卓越质量
Mistral Small 4 119B (119B parameters) requires approximately 79.5 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 6.5B 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 92 GB of VRAM.
快速开始
— 复制粘贴即可本地运行Copy-paste commands to run Mistral Small 4 119B on your machine.
Run
lms load Mistral-Small-4-119B-2603 && lms server startQuick specs
Parameters119B (6.5B active)
Architecturemoe (MoE)
Context256K tokens
Modalitytext+vision
Min RAM46.4 GB
Rec. RAM72.6 GB (Q4_K_M)
LicenseMistral Research License
FamilyMistral Small
✓ Vision✓ Code✓ Chat✓ Reasoning
About this model
- •MoE: 128 experts, 4 active
- •119B parameters: , with 6.5B activated per token
- •256k context length:
- •Multimodal input: Accepts both text and image input, with text output
- •Instruct and Reasoning functionalities: with function calls (reasoning effort configurable per request)
相关模型
快速推荐
最佳硬件
Mistral Small 4 119B 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 | 46.4 GB | Low | — |
Q3_K_S | 3 | 58.3 GB | Low | — |
NVFP4 | 4 | 66.6 GB | Medium | — |
Q4_K_M | 4 | 72.6 GB | Medium | — |
Q5_K_M | 5 | 85.7 GB | High | — |
Q6_K | 6 | 97.6 GB | High | — |
Q8_0 | 8 | 127.3 GB | Very High | — |
F16 | 16 | 244.0 GB | Maximum | — |
Quality benchmarks
Mistral Small 4 119B benchmark scores
Coding
SWE-bench Verified—
HumanEval+—
Aider Polyglot—
LiveCodeBench63.6%
Reasoning
MMLU-Pro78.0%
GPQA Diamond71.2%
MATH-500—
ARC Challenge—
Source: official · 2026-03-16
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
Weights72.6 GB
KV Cache5.4 GB
Runtime0.9 GB
Headroom0.6 GB
常见问题
FAQ — Mistral Small 4 119B
另请参阅