nvidia/Qwen3.8-Flash-Next-NVFP4 download history
nvidia/Qwen3.8-Flash-Next-NVFP4 is an 119.6B-parameter image text to text model by nvidia. In the last 30 days it was downloaded 295,068 times (76,895 in the last 7 days), and 295,088 times in total.
It ranks #1,170 on the Hub by monthly downloads and #191 among image text to text models.
It has 336 likes, 37 of them in the last week.
It is a quantization of Qwen/Qwen3.8-Flash-Next.
10 models build on Qwen3.8-Flash-Next-NVFP4: 6 quantized, 3 fine-tuned, 0 adapters and 1 merges. Together with the original they were downloaded 301,013 times in the last 30 days. See the Qwen3.8-Flash-Next-NVFP4 galaxy.
Most downloaded derivatives
- CompiledThoughts/Qwen3.8-Flash-Next-NVFP4-Q8_0 (quantized), 1.8K downloads in 30 days
- PixelML/Qwen3.8-Flash-Next-NVFP4-DFlash (finetune), 1.1K downloads in 30 days
- drowzeys/keys-Qwen3.8-Flash-Next-NVFP4-dual-ablit-house-qsa-L3-47 (finetune), 923 downloads in 30 days
- oakmindai/Qwen3.8-Flash-Next-NVFP4-FTW (quantized), 629 downloads in 30 days
- Shinrali/Qwen3.8-Flash-Next-NVIDIA-Hybrid-Single-Spark (quantized), 621 downloads in 30 days
- dicksondickson/Qwen3.8-Flash-Next-NVFP4-reshard-mtp-fix (quantized), 494 downloads in 30 days
- wrldsuksgo2mars/Qwen3.8-Flash-Next-EXL3-K4.25-PLE-FP8-v1 (merge), 129 downloads in 30 days
- JasonW2025/Qwen3.8-Flash-Next-NVFP4-Calibrated-KV (quantized), 23 downloads in 30 days
- gitcommit90/Qwen3.8-Flash-Next-NVFP4-DenseFP8-One-Spark (finetune), 0 downloads in 30 days