Qwen/QwQ-32B download history
Qwen/QwQ-32B is a 32.8B-parameter text generation model by Qwen. In the last 30 days it was downloaded 56,293 times (8,738 in the last 7 days), and 3,578,821 times in total.
It ranks #3,612 on the Hub by monthly downloads and #809 among text generation models.
It has 2,966 likes, 1 of them in the last week.
It is a fine-tune of Qwen/Qwen2.5-32B.
750 models build on QwQ-32B: 492 quantized, 98 fine-tuned, 64 adapters and 96 merges. Together with the original they were downloaded 391,949 times in the last 30 days. See the QwQ-32B galaxy.
Most downloaded derivatives
- MaziyarPanahi/QwQ-32B-GGUF (quantized), 145.6K downloads in 30 days
- lmstudio-community/QwQ-32B-MLX-8bit (quantized), 27.6K downloads in 30 days
- Qwen/QwQ-32B-GGUF (quantized), 14.2K downloads in 30 days
- Qwen/QwQ-32B-AWQ (quantized), 11.2K downloads in 30 days
- lmstudio-community/QwQ-32B-GGUF (quantized), 5.7K downloads in 30 days
- bartowski/Qwen_QwQ-32B-GGUF (quantized), 4.8K downloads in 30 days
- Alibaba-NLP/WebDancer-32B (finetune), 3.4K downloads in 30 days
- unsloth/QwQ-32B-GGUF (quantized), 2.9K downloads in 30 days
- gaianet/QwQ-32B-GGUF (quantized), 1.2K downloads in 30 days
- brittlewis12/QwQ-32B-GGUF (quantized), 906 downloads in 30 days
- Mungert/QwQ-32B-ArliAI-RpR-v4-GGUF (quantized), 887 downloads in 30 days
- Mungert/Kevin-32B-GGUF (quantized), 696 downloads in 30 days