This is a MXFP8 quantization of Qwen/Qwen3.5-35B-A3B, generated by AutoRound. Please follow the license of the original model. — Scheme: MXFP8 — Method: AutoRound — Base model: Qwen/Qwen3.5-35B-A3B Inference: load this repo with a vllm build that supports the MXFP8 format (day-0 architectures may need the model card’s custom image/branch — check the quantize command above for the environment used). Produced with autoquant-agent — agent-driven quantize + evaluate + self-heal.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: INCModel3
Теги: qwen3_5_moe, quantized, mxfp8, autoround, autoquant-agent, conversational, compressed-tensors
Лайков: 3 | Загрузок: 33
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
