NVFP4 quantisation of LuffyTheFox/Qwen3.8-27B-Uncensored-Genesis-GGUF, built with advanced-gguf-quantizer (a llama.cpp fork focused on NVFP4 quantization). This is the Genesis-repaired version of HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive — Luffy’s tensor repair applied to the HauhauCS uncensored base. v4 uses —nvfp4-inline-scales-only to emit native inline UE4M3 scales without separate .scale/.inputscale` tensors. Required for LM Studio / Pelican and other runtimes that do not support the extended NVFP4 scale tensor contract. Imatrix variants will follow after the plain v4 is confirmed working in target runtimes. — blk..attnnorm.weight, blk..postattentionnorm.weight — blk..attnqnorm.weight, blk..attnknorm.weight — blk..ssmnorm.weight, blk..nextn..norm.weight — outputnorm.weight — blk..ssmconv1d.weight, blk..ssmdt.bias, blk..ssma For runtimes without FastMTP support, use Qwen3.8-27B-Uncensored-Genesis-NVFP4-v4-noMTP.gguf. The MTP variant enables speculative decoding (—spec-type draft-mtp where supported). — Set K cache and V cache quantization to F16 — Vision support requires the mmproj file from the source repository — Blackwell (RTX 50xx): native FP4 path, fastest -…
Модальности:
Генерация текста Компьютерное зрение
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: jan1k
Теги: gguf, nvfp4, fp4, blackwell, llama.cpp, qwen3.8, uncensored, fastmtp
Лайков: 3 | Загрузок: 225
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.