Specialized and Enhanced UNCENSORED/HERETIC GGUF quants for the new GLM-4.7-Flash, 30B-A3B MOE, mixture of experts model. This model can be run on the GPU(s) and/or CPU due to 4 experts activated (appox 2B parameters active). De-censoring by Heretic (special thanks to «Olafangensan») seems to have reduced the size of thinking blocks in some cases and/or «focused» the model more. That being said, I suggest min context of 8k-16K as final outputs (post thinking) can be long and detailed and in a number of cases has been observed «polishing» the final output one or more times IN the output section. https://huggingface.co/DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF Quants and Imatrixes computed using latest LLAMACPP (commit: 7789, Jan 21 2026) which contains specific fixes for this model. Quants prior to this commit (as well as Imatrix generation) performed poorly (re-quanization and re-imatrix generation are required). Also note there are some issues with Flash Attn and low token generation speed (as Flash is offloaded to CPU in some cases). Disable Flash Attn until this issue is resolved / makes its way thru the «llamacpp / ai pipeline». Specialized quants…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат Генерация кода
Задача: Генерация текста
Автор: wegrow
Теги: gguf, GLM 4.7 Flash, thinking, reasoning, NEO Imatrix, MAX Quants, 16 bit precision output tensor, heretic
Лайков: 3 | Загрузок: 285
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
