Qwen/Qwen3-4B
Qwen3 4B dense model with hybrid thinking/non-thinking modes — fits on a single TPU v6e chip or one GPU.
Verified on TPU v6e (Trillium) with BF16 on a single chip
Qwen3 4B dense model with hybrid thinking/non-thinking modes — fits on a single TPU v6e chip or one GPU.
Verified on TPU v6e (Trillium) with BF16 on a single chip
View on HuggingFace
View on ModelScope