AI is happening. The future is updating.Qwen3.8-Flash-Next-MLX-4bit-MTP
A uniform 4-bit MLX conversion of Qwen/Qwen3.8-Flash-Next , rebuilt directly from the official BF16 checkpoint with the model's native MTP draft block preserved. This repository contains the standard uniform 4-bit release. Eligible language-model and native-MTP modules use MLX affine quantisation at group size 32. Multimodal modules and MoE router gates remain in BF16. Group size 32 also covers the model's 160-wide hashed n-gram embedding tables. The upstream tokenizer, chat template, vision processor, generation configuration, licence, and native MTP configuration are retained.
A uniform 4-bit MLX conversion of Qwen/Qwen3.8-Flash-Next , rebuilt directly from the official BF16 checkpoint with the model's native MTP draft block preserved. This repository contains the standard uniform 4-bit release. Eligible language-model and native-MTP modules use MLX affine quantisation at group size 32. Multimodal modules and MoE router gates remain in BF16. Group size 32 also covers the model's 160-wide hashed n-gram embedding tables. The upstream tokenizer, chat template, vision processor, generation configuration, licence, and native MTP configuration are retained.