Qwen/Qwen3.8-2.4T-A95B download history

Qwen/Qwen3.8-2.4T-A95B is a 2446.2B-parameter text generation model by Qwen. In the last 30 days it was downloaded 33,969 times (6,281 in the last 7 days), and 84,341 times in total.

It ranks #4,528 on the Hub by monthly downloads and #1,027 among text generation models.

It has 1,280 likes, 17 of them in the last week.

43 models build on Qwen3.8-2.4T-A95B: 39 quantized, 4 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 107,358 times in the last 30 days. See the Qwen3.8-2.4T-A95B galaxy.

Most downloaded derivatives

• unsloth/Qwen3.8-2.4T-A95B-GGUF (quantized), 8.2K downloads in 30 days
• Qwen/Qwen3.8-2.4T-A95B-FP8 (quantized), 8.2K downloads in 30 days
• Inferact/Qwen3.8-2.4T-A95B-NVFP4 (quantized), 5K downloads in 30 days
• inference-optimization/Qwen3.8-1.0B-A0.6B (finetune), 4.5K downloads in 30 days
• nvidia/Qwen3.8-2.4T-A95B-NVFP4 (quantized), 2.2K downloads in 30 days
• RadixArk/Qwen3.8-2.4T-A95B-NVFP4 (quantized), 1.1K downloads in 30 days
• RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50 (quantized), 1.1K downloads in 30 days
• RedHatAI/Qwen3.8-2.4T-A95B-NVFP4 (quantized), 778 downloads in 30 days
• RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-25 (quantized), 730 downloads in 30 days
• pipenetwork/Qwen3.8-2.4T-A95B-MLX-reap60-3bit (quantized), 661 downloads in 30 days
• m8than/Qwen38-2.4T-GG (quantized), 563 downloads in 30 days
• pipenetwork/Qwen3.8-2.4T-A95B-MLX-reap50-3bit (quantized), 560 downloads in 30 days

Open Qwen/Qwen3.8-2.4T-A95B on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.