Alibaba
Qwen 3 30B A3B
前沿
1.1M下载量812点赞Apr 2025发布日期131K tokens上下文Apache 2.0许可证94 卓越质量
Qwen 3 30B A3B (30.5B parameters) requires approximately 21.9 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 3.299999952316284B 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 26 GB of VRAM.
快速开始
— 复制粘贴即可本地运行Copy-paste commands to run Qwen 3 30B A3B on your machine.
Run
ollama run qwen3:30b-a3bQuick specs
Parameters30.5B (3.3B active)
Architecturemoe (MoE)
Context131K tokens
Modalitytext
Min RAM11.9 GB
Rec. RAM18.6 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
✓ Chat✓ Reasoning
About this model
- •Significant improvements: in general capabilities, including **instruction following, logical reasoning, text comprehension, mathematics, science,...
- •Substantial gains: in long-tail knowledge coverage across multiple languages
- •Markedly better alignment: with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text...
- •Enhanced capabilities: in 256K long-context understanding
相关模型
快速推荐
最佳硬件
Qwen 3 30B A3B 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 | 11.9 GB | Low | — |
Q3_K_S | 3 | 14.9 GB | Low | — |
NVFP4 | 4 | 17.1 GB | Medium | — |
Q4_K_M | 4 | 18.6 GB | Medium | — |
Q5_K_M | 5 | 22.0 GB | High | — |
Q6_K | 6 | 25.0 GB | High | — |
Q8_0 | 8 | 32.6 GB | Very High | — |
F16 | 16 | 62.5 GB | Maximum | — |
Quality benchmarks
Qwen 3 30B A3B benchmark scores
Coding
SWE-bench Verified—
HumanEval+—
Aider Polyglot—
LiveCodeBench62.6%
Reasoning
MMLU-Pro80.9%
GPQA Diamond73.4%
MATH-500—
ARC Challenge—
General
Chatbot Arena—
IFEval88.9%
Source: official · 2025-07-14
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
Weights18.6 GB
KV Cache1.5 GB
Runtime1.2 GB
Headroom0.6 GB
常见问题
FAQ — Qwen 3 30B A3B
另请参阅