Small fast 'System 1' · Alibaba Qwen
Qwen3 1.7B
Small Qwen3 with thinking mode; a good draft model for speculative decoding.
Datasheet
Maker | Alibaba Qwen |
|---|---|
Parameters | 2.03 BVerifiedsafetensors.total from the HF API Source |
Licence | Apache-2.0Verified |
Access | Public download |
Task (HF pipeline) | text-generation |
First published on HF | 2025-04-27 |
Last updated on HF | 2025-07-26 |
Weights in memory | 4.1 GB at 16-bit · 1.2 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
BFCL V4, overall accuracy
No comparable public score for this benchmark yet. We will not estimate one.
The description summarises the model card at https://huggingface.co/Qwen/Qwen3-1.7B. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.