DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF — new model trending #30 on Hugging Face
DavidAU releases Qwen3.8-27B-TWIN-TURBO, an uncensored GGUF fine-tune claiming sharply reduced thinking tokens and self-reported benchmark gains.
A new community fine-tune of Qwen3.8-27B, built with Unsloth via 'Cold Fusion' and 'Fable Fusion 711' methods, is trending #30 on Hugging Face. The author claims arc-c scores of 709 in 8-bit and 701 in 4-bit, exceeding the base Qwen3.8-27B, while cutting thinking tokens to between 1/2 and 1/20 of baseline. The release provides regular and MTP Neo/NEO MAX GGUF quants, five switchable reasoning modes plus five zero-reasoning instruct modes, and a lightly uncensored variant. All benchmark claims are author-reported and not independently verified.
25