nvidia/Qwen3.8-Flash-Next-NVFP4
Quantization vs Qwen/Qwen3.8-Flash-Next. nvidia/Qwen3.8-Flash-Next-NVFP4 is a quantized version of the other (F8_E4M3/U8).
7 derivatives checked
- CompiledThoughts/Qwen3.8-Flash-Next-NVFP4-Q8_0: Not comparable yet
- Maximilian228/Qwen3.8-Flash-Next-NVIDIA-NVFP4-Strata: Quantization
- PixelML/Qwen3.8-Flash-Next-NVFP4-DFlash: Quantization
- Shinrali/Qwen3.8-Flash-Next-NVIDIA-Hybrid-Single-Spark: LoRA-style
- dicksondickson/Qwen3.8-Flash-Next-NVFP4-reshard-mtp-fix: Same weights, repacked
- oakmindai/Qwen3.8-Flash-Next-NVFP4-FTW: Same weights, repacked (fewer layers)
- wrldsuksgo2mars/Qwen3.8-Flash-Next-EXL3-K4.25-PLE-FP8-v1: Different architecture