Qwen/Qwen3.8-Flash-Next-FP8 download history
Qwen/Qwen3.8-Flash-Next-FP8 is an 180.0B-parameter image text to text model by Qwen. In the last 30 days it was downloaded 410,581 times (34,516 in the last 7 days), and 596,437 times in total.
It ranks #902 on the Hub by monthly downloads and #138 among image text to text models.
It has 246 likes, 15 of them in the last week.
It is a quantization of Qwen/Qwen3.8-Flash-Next.
14 models build on Qwen3.8-Flash-Next-FP8: 14 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 462,203 times in the last 30 days. See the Qwen3.8-Flash-Next-FP8 galaxy.
Most downloaded derivatives
- julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF (quantized), 8.7K downloads in 30 days
- dealignai/Qwen3.8-Flash-Next-UNCENSORED-FP8 (quantized), 1.2K downloads in 30 days
- dealignai/Qwen3.8-Flash-Next-ABLITERATED-FP8 (quantized), 999 downloads in 30 days
- HaberstrohSystems/Qwen3.8-Flash-Next-int2-mixed-AutoRound-24GB-SGLang (quantized), 617 downloads in 30 days
- Soomin33/Qwen3.8-Flash-Next-FP6 (quantized), 272 downloads in 30 days
- Soomin33/Qwen3.8-Flash-Next-FP6-INT8 (quantized), 229 downloads in 30 days
- Yanun/Qwen3.8-Flash-Next-MXFP4 (quantized), 204 downloads in 30 days
- Jiunsong/SuperQwen3.8-Flash-Next-abliterated-FP8-DGX-Spark (quantized), 193 downloads in 30 days
- microperceptron/Qwen3.8-Flash-Next-UNCENSORED-FP8 (quantized), 117 downloads in 30 days
- MJPansa/Qwen3.8-Flash-Next-MXFP4-FP8-R12 (quantized), 79 downloads in 30 days
- fridaystreet/Qwen3.8-Flash-Next-FP6-INT8 (quantized), 19 downloads in 30 days
- someguystrainingmodels/decision-model-large (quantized), 17 downloads in 30 days