hugpadhugpad

nerkyor / Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-MTP-NVFP4

Text Generation03Updated Sep 12, 2026
Hugging Face

Downloads

0

Likes

3

Last updated

Sep 12, 2026

License

apache-2.0

The bundled DFlash2 draft is now a pre-quantized static FP8 compressed-tensors checkpoint, not a BF16 checkpoint carrying an FP8 directory label. model.safetensors is 2,407,027,720 bytes (SHA256 1f3636a32d866f8ebc7f422d63f9247126ebb6d2566d3e0da327d81dd8fa25d1). Its audited ten…

Tasks & library

  • text generation

Tags

  • qwen3.8
  • nvfp4
  • mixed-precision
  • modelopt
  • sglang
  • mtp

Technical specifications

ParametersNot available
LibraryNot available
Languagesen, zh
Base modelQwen/Qwen3.8-27B
Licenseapache-2.0