Qwen/Qwen3-235B-A22B-Thinking-2507 download history
Qwen/Qwen3-235B-A22B-Thinking-2507 is a 235.1B-parameter text generation model by Qwen. In the last 30 days it was downloaded 17,874 times (5,540 in the last 7 days), and 654,698 times in total.
It ranks #6,065 on the Hub by monthly downloads and #1,387 among text generation models.
It has 410 likes.
109 models build on Qwen3-235B-A22B-Thinking-2507: 86 quantized, 21 fine-tuned, 2 adapters and 0 merges. Together with the original they were downloaded 82,361 times in the last 30 days. See the Qwen3-235B-A22B-Thinking-2507 galaxy.
Most downloaded derivatives
- Qwen/Qwen3-235B-A22B-Thinking-2507-FP8 (quantized), 37.4K downloads in 30 days
- unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF (quantized), 4.2K downloads in 30 days
- Mungert/MiroThinker-1.7-mini-GGUF (quantized), 2K downloads in 30 days
- bartowski/Qwen_Qwen3-235B-A22B-Thinking-2507-GGUF (quantized), 1.5K downloads in 30 days
- nvidia/Qwen3-Nemotron-235B-A22B-GenRM (finetune), 1K downloads in 30 days
- miromind-ai/MiroThinker-1.7-mini (finetune), 635 downloads in 30 days
- lmstudio-community/Qwen3-235B-A22B-Thinking-2507-MLX-8bit (quantized), 460 downloads in 30 days
- QuantTrio/Qwen3-235B-A22B-Thinking-2507-AWQ (quantized), 398 downloads in 30 days
- John1604/Qwen3-235B-A22B-Thinking-2507-gguf (quantized), 387 downloads in 30 days
- nvidia/Qwen3-Nemotron-235B-A22B-GenRM-2603 (finetune), 358 downloads in 30 days
- nvidia/Qwen3-235B-A22B-Thinking-2507-NVFP4 (quantized), 341 downloads in 30 days
- lmstudio-community/Qwen3-235B-A22B-Thinking-2507-MLX-4bit (quantized), 246 downloads in 30 days
Open Qwen/Qwen3-235B-A22B-Thinking-2507 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.