Small fast 'System 1' · Alibaba Qwen

Qwen3 0.6B

Hugging Face: Qwen/Qwen3-0.6B · checked 2026-10-13

The smallest Qwen3: routing, classification and form-filling at hundreds of tok/s.

Datasheet

Maker	Alibaba Qwen
Parameters	752 MVerifiedsafetensors.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	1.5 GB at 16-bit · 0.5 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build.

Benchmark

23.93%

BFCL V4, overall accuracy · #1 of 3 scored in this category

Qwen3-0.6B (FC) row, rank 92. Source

See the full small fast 'system 1' ranking

The description summarises the model card at https://huggingface.co/Qwen/Qwen3-0.6B. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.