MODEL REFERENCE / Qwen
Qwen/Qwen3-4B
Qwen3 4B dense model with hybrid thinking/non-thinking modes — fits on a single TPU v6e chip, one GPU or one Xeon 6 NUMA node.
Verified on TPU v6e (Trillium) with BF16 on a single chip
View on HuggingFace
View on ModelScope02 / Configure
Configure serving
Choose engine, hardware and deployment options. The command updates as you go.
03 / Understand