Intel/Qwen3.8-Flash-Next-W4A16-AutoRound download history
Intel/Qwen3.8-Flash-Next-W4A16-AutoRound is a 75.4B-parameter image text to text model by Intel. In the last 30 days it was downloaded 46,428 times (9,874 in the last 7 days), and 58,254 times in total.
It ranks #3,925 on the Hub by monthly downloads and #501 among image text to text models.
It has 27 likes, 1 of them in the last week.
It is a quantization of Qwen/Qwen3.8-Flash-Next.
9 models build on Qwen3.8-Flash-Next-W4A16-AutoRound: 8 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 56,323 times in the last 30 days. See the Qwen3.8-Flash-Next-W4A16-AutoRound galaxy.
Most downloaded derivatives
- albucino/Qwen3.8-Flash-Next-W4A16-FP8PLE (quantized), 5.4K downloads in 30 days
- azampatti/Qwen3.8-Flash-Next-125B-A5B-INT4-AutoRound (quantized), 1.8K downloads in 30 days
- Saren/Qwen3.8-Flash-Next-W4A16-AutoRound-hybrid (quantized), 1.1K downloads in 30 days
- todiadiyatmo/Qwen3.8-Flash-Next-W4A16-Attn8-FP8PLE (quantized), 868 downloads in 30 days
- hampsonw/Qwen3.8-Flash-Next-W4A16-AutoRound-MTP-INT4-Experts (quantized), 150 downloads in 30 days
- ethones2012/Qwen3.8-Flash-Next-W4A16-FP8PLE (quantized), 16 downloads in 30 days
- Jon-Nielsen/Qwen3.8-Flash-Next-Merlin-3090-Serving-Kit (finetune), 0 downloads in 30 days
Open Intel/Qwen3.8-Flash-Next-W4A16-AutoRound on Hugging Face