This model was converted to MLX format and quantized from Qwen3.6-27B using oMLX. Unlike the Qwen3.6-35B-A3B collection, work on the full Qwen3.6-27B 4×4 table is still ongoing. So if you see a 404 link below, feel free to ask me to prioritize it. «VL» is Vision-Language, meaning quantization preserves the original model’s multimodality. «FP16» is an M1/M2 Apple Silicon tweak that delivers a very noticeable prompt processing boost, because older M-series lack native BF16 hardware support. See «Metal FP32 Vs BF16 Vs FP16 benchmark» for details. No «FP16» means quantization is better suited for M3+ Apple Silicon. [01]: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-oQ8 [02]: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-oQ6 [03]: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-oQ5 [04]: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-oQ4 [05]: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-VL-oQ8 [06]: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-VL-oQ6 [07]: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-VL-oQ5 [08]: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-VL-
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: deepsweet
Теги: mlx, qwen3_5, conversational, en, 4-bit
Лайков: 4 | Загрузок: 206
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
