Sakura 27B is an experimental post-quantization compressed GGUF based on Qwen3.8-27B-EfficientThink-SimPO-Q2-LynnStyle.gguf. The exact source GGUF is Q2-LynnStyle/Qwen3.8-27B-EfficientThink-SimPO-Q2-LynnStyle.gguf from nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUF. The foundation model is Qwen/Qwen3.8-27B. — Parameters: 26.9B — Source checkpoint: Qwen3.8-27B-EfficientThink-SimPO-Q2-LynnStyle.gguf — Source size: 12,999,977,600 Bytes (12.107 GiB) — Sakura size: 10,672,552,800 Bytes (9.940 GiB) — Reduction: 17.90% Speed and memory were measured on an RTX 5090 32 GB using the same setup for Base and Sakura. Perplexity is worse for Sakura. MMLU is lower by 2.92 points, while ARC-Easy is higher by 6.20 points. These measurements are not a claim of general quality superiority over the base model. Sakura requires the PrismML llama.cpp fork with support for its custom GGUF/runtime operations. Stock/upstream llama.cpp cannot load this GGUF. The verified build at the time of testing was 1a07bfa5f on the prism branch. Compatibility with LM Studio and Strix Halo has not been tested and is not claimed. — Perplexity regression relative to the…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: webmp3
Теги: gguf, qwen, experimental, sakura, endpoints_compatible, imatrix, conversational
Лайков: 3 | Загрузок: 369
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
