Qwen/Qwen3-32B download history
Qwen/Qwen3-32B is a 32.8B-parameter text generation model by Qwen. In the last 30 days it was downloaded 3,986,798 times (819,537 in the last 7 days), and 59,116,316 times in total.
It ranks #102 on the Hub by monthly downloads and #21 among text generation models.
It has 754 likes, 3 of them in the last week.
1,649 models build on Qwen3-32B: 515 quantized, 684 fine-tuned, 421 adapters and 29 merges. Together with the original they were downloaded 6,520,966 times in the last 30 days. See the Qwen3-32B galaxy.
Most downloaded derivatives
- Qwen/Qwen3-32B-AWQ (quantized), 1M downloads in 30 days
- RedHatAI/Qwen3-32B-NVFP4 (quantized), 383K downloads in 30 days
- MaziyarPanahi/Qwen3-32B-GGUF (quantized), 240.1K downloads in 30 days
- Qwen/Qwen3-32B-FP8 (quantized), 185.3K downloads in 30 days
- unsloth/Qwen3-32B-GGUF (quantized), 114.9K downloads in 30 days
- Qwen/Qwen3-32B-GGUF (quantized), 97.8K downloads in 30 days
- unsloth/Qwen3-32B-bnb-4bit (quantized), 62.9K downloads in 30 days
- lmstudio-community/Qwen3-32B-MLX-4bit (quantized), 49.1K downloads in 30 days
- lmstudio-community/Qwen3-32B-MLX-8bit (quantized), 48.7K downloads in 30 days
- nvidia/Qwen3-32B-NVFP4 (quantized), 14.4K downloads in 30 days
- bartowski/Qwen_Qwen3-32B-GGUF (quantized), 11.5K downloads in 30 days
- unsloth/Qwen3-32B-unsloth-bnb-4bit (quantized), 10.9K downloads in 30 days