Qwen/Qwen3.8-Flash-Next-FP8
Quantization vs Qwen/Qwen3.8-Flash-Next. Qwen/Qwen3.8-Flash-Next-FP8 is a quantized version of the other (F8_E4M3/BF16).
9 derivatives checked
- julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF: Quantization
- SkyIsNotGreen/Scion-FlashNext-176B-A6B: Quantization
- dealignai/Qwen3.8-Flash-Next-UNCENSORED-FP8: Abliterated
- dealignai/Qwen3.8-Flash-Next-ABLITERATED-FP8: Abliterated
- HaberstrohSystems/Qwen3.8-Flash-Next-int2-mixed-AutoRound-24GB-SGLang: Different architecture
- Soomin33/Qwen3.8-Flash-Next-FP6-INT8: Different architecture
- Soomin33/Qwen3.8-Flash-Next-FP6: Different architecture
- Jiunsong/SuperQwen3.8-Flash-Next-abliterated-FP8-DGX-Spark: Abliterated
- microperceptron/Qwen3.8-Flash-Next-UNCENSORED-FP8: Abliterated
5 other repos hold byte-for-byte identical weight files.