Qwen3 30B-A3B
Alibaba · Text generation · MoE 30B-A3B · 131k context · Released 29 April 2025
Commercial use permitted
Open weights
Runs on CPU
Apple Silicon
In a mixture-of-experts model, only a fraction of the parameters are used for any given token. Qwen3 30B-A3B activates 3B of its 30B parameters at a time, which means it runs at roughly the speed of a much smaller model while drawing on the knowledge of a larger one. The catch is memory: all 30B parameters must still be loaded, so it needs the memory of a 30B model even though it runs like a 3B one.
Strengths
- Much faster generation than a dense model of similar quality
- Strong reasoning for the speed, with optional thinking mode
- Apache 2.0, long 128k context
Weaknesses
- Needs the memory of a 30B model despite only 3B being active
- A dense 32B can edge it on peak quality at similar memory
- Thinking mode adds latency and token use
Hardware requirements
| Quantisation | Approx. VRAM | Notes |
|---|---|---|
| Q4_K_M | ~18GB | Fits a 24GB card with some room for context |
| Q8_0 | ~32GB | Near-lossless, needs 36GB or more |
| FP16 | ~61GB | Full precision, server or multi-GPU territory |
Also runs on CPU (slower). Optimised builds available for Apple Silicon.
Licence
Apache 2.0 — read the licence
Availability
- Official page
- Hugging Face
- ollama run qwen3:30b-a3b
Recommended for
- Users who want fast generation with strong quality on a 24GB card
- Mac users who want responsive local inference at larger model quality
- Interactive use where generation speed matters
Related guides
Glossary
Catalogue entry last verified 30 July 2026. Specifications change; verify anything you are about to spend money on.