Qwen/Qwen3-Next-80B-A3B-Thinking download history
Qwen/Qwen3-Next-80B-A3B-Thinking is an 81.3B-parameter text generation model by Qwen. In the last 30 days it was downloaded 41,546 times (8,193 in the last 7 days), and 2,512,186 times in total.
It ranks #4,125 on the Hub by monthly downloads and #931 among text generation models.
It has 496 likes.
91 models build on Qwen3-Next-80B-A3B-Thinking: 66 quantized, 19 fine-tuned, 4 adapters and 2 merges. Together with the original they were downloaded 165,401 times in the last 30 days. See the Qwen3-Next-80B-A3B-Thinking galaxy.
Most downloaded derivatives
- bartowski/Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF (quantized), 77.5K downloads in 30 days
- unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF (quantized), 16K downloads in 30 days
- nvidia/Qwen3-Next-80B-A3B-Thinking-NVFP4 (quantized), 3.9K downloads in 30 days
- Qwen/Qwen3-Next-80B-A3B-Thinking-FP8 (quantized), 2.3K downloads in 30 days
- mradermacher/Qwen3-Next-80B-A3B-Thinking-i1-GGUF (quantized), 1.4K downloads in 30 days
- mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit (quantized), 1.3K downloads in 30 days
- mlx-community/Qwen3-Next-80B-A3B-Thinking-8bit (quantized), 1.1K downloads in 30 days
- cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit (quantized), 1K downloads in 30 days
- lmstudio-community/Qwen3-Next-80B-A3B-Thinking-GGUF (quantized), 801 downloads in 30 days
- a4lg/Qwen3-Next-80B-A3B-Thinking-MTP-ONLY-GGUF (quantized), 377 downloads in 30 days
- lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-4bit (quantized), 371 downloads in 30 days
- INC4AI/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound (quantized), 346 downloads in 30 days