Coding · Alibaba Qwen
Qwen3 Coder 30B-A3B
Mixture-of-experts coder with 3B active parameters: fast on 24 GB cards and unified memory.
Datasheet
Maker | Alibaba Qwen |
|---|---|
Parameters | 30.53 BVerifiedsafetensors.total from the HF API Source |
Licence | Apache-2.0Verified |
Access | Public download |
Task (HF pipeline) | text-generation |
First published on HF | 2025-07-31 |
Last updated on HF | 2025-12-03 |
Weights in memory | 61 GB at 16-bit · 19 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build. |
Benchmark
Not yet measured
SWE-bench Verified, % resolved
No comparable public score for this benchmark yet (The card reports results as an image only; no text value captured). We will not estimate one.
Used in
The description summarises the model card at https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.