Qwen3.8-27B FP8 & NVFP4 quants of Qwen/Qwen3.8-27B. Reserved ahead of the upstream release — weights land as soon as the base model ships. huginnfork/Qwen3.8-27B-FP8 Image-Text-to-Text • 28B • Updated 15 days ago • 8.66k • 37 huginnfork/Qwen3.8-27B-NVFP4A16 Image-Text-to-Text • 28B • Updated 15 days ago • 7.22k • 20
Ornith-1.0-35B FP8 & NVFP4 quants of the 256-expert Ornith-1.0-35B MoE. Routers, SSM block and vision tower stay bf16. Serve in vLLM or SGLang. huginnfork/Ornith-1.0-35B-FP8 Image-Text-to-Text • 35B • Updated Jun 30 • 122 huginnfork/Ornith-1.0-35B-NVFP4A16 Image-Text-to-Text • 21B • Updated Jun 30 • 15
Qwen3.8-27B FP8 & NVFP4 quants of Qwen/Qwen3.8-27B. Reserved ahead of the upstream release — weights land as soon as the base model ships. huginnfork/Qwen3.8-27B-FP8 Image-Text-to-Text • 28B • Updated 15 days ago • 8.66k • 37 huginnfork/Qwen3.8-27B-NVFP4A16 Image-Text-to-Text • 28B • Updated 15 days ago • 7.22k • 20
Ornith-1.0-35B FP8 & NVFP4 quants of the 256-expert Ornith-1.0-35B MoE. Routers, SSM block and vision tower stay bf16. Serve in vLLM or SGLang. huginnfork/Ornith-1.0-35B-FP8 Image-Text-to-Text • 35B • Updated Jun 30 • 122 huginnfork/Ornith-1.0-35B-NVFP4A16 Image-Text-to-Text • 21B • Updated Jun 30 • 15
huginnfork/Qwen3.6-27B-uncensored-heretic-v2-mtp-FP8 Image-Text-to-Text • 28B • Updated about 1 month ago • 1.13k • 5
huginnfork/Qwen3.6-27B-uncensored-heretic-v2-mtp-NVFP4A16 Image-Text-to-Text • 20B • Updated Apr 27 • 108 • 2