TheUnderscore/Swift-1.5-Qwen3.8-27b-NVFP4-W4ATTN-AWQ Image-Text-to-Text • 28B • Updated 5 days ago • 39
TheUnderscore/Swift-1.5-Qwen3.8-27b-NVFP4-W4ATTN-AWQ Image-Text-to-Text • 28B • Updated 5 days ago • 39
TheUnderscore/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-W4A16-AWQ Image-Text-to-Text • 10B • Updated 18 days ago • 11.8k
TheUnderscore/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-W4A16-AWQ Image-Text-to-Text • 28B • Updated 18 days ago • 717 • 2
TheUnderscore/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-W4A16-AWQ Image-Text-to-Text • 28B • Updated 18 days ago • 717 • 2
view reply Do you plan to update the base model files? Also, what changes did you make weight-wise? If it's just chat template(s), that'd be good to know so I can update my quant by extracting from a GGUF.