Alibaba · 30B (3.3B active) · Mixture of Experts
MoE with only 3.3B active — extremely efficient Check if your GPU or Mac can run Qwen 3 30B-A3B locally — 16.8 GB min, 27.9 GB recommended.
Mixture of Experts
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 10.1 GB | low | — |
| Q3_K_M | 3 | 13.9 GB | moderate | — |
| Q4_K_M | 4 | 15.9 GB | good | — |
| Q5_K_M | 5 | 19.7 GB | good | — |
| Q6_K | 6 | 23.6 GB | excellent | — |
| Q8_0 | 8 | 31.2 GB | excellent | — |
| F16 | 16 | 62 GB | lossless | — |
About this model
Qwen 3 is the latest generation of large language models in Qwen series, with newly updated versions of the 30B and 235B models:
New 30B model
ollama run qwen3:30b
New 235B model
ollama run qwen3:235b
Overview
The Qwen 3 family is a comprehensive suite of dense and mixture-of-experts (MoE) models. The flagship model, Qwen3-235B-A22B, achieves competitive results in benchmark evaluations of coding, math, general capabilities, etc., when compared to other top-tier models such as DeepSeek-R1, o1, o3-mini, Grok-3, and Gemini-2.5-Pro. Additionally, the small MoE model, Qwen3-30B-A3B, outcompetes QwQ-32B with 10 times of activated parameters, and even a tiny model like Qwen3-4B can rival the performance of Qwen2.5-72B-Instruct.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Reference
Can I run Qwen 3 30B-A3B locally?
- Can I run Qwen 3 30B-A3B locally?
- Qwen 3 30B-A3B needs about 16.8 GB of memory at a minimum and 27.9 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Qwen 3 30B-A3B need?
- At Q4_K_M, Qwen 3 30B-A3B uses about 15.9 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.