LLM EXPLORER 59,962 MODELS INDEXED

Qwen3.8 Flash Next MXFP4 MLX by txgsync

By txgsync · 558 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next MXFP4 MLX is an open-source language model by txgsync. Features: 33.6b LLM, VRAM: 99.7GB, License: other, LLM Explorer Score: 0.32.

  4-bit   Apple-silicon Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Image-text-to-text   Long-context   Mlx   Mlx-vlm   Mxfp4   Omlx   Quantized   Qwen3.8   Qwen4   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow   Vision   Vision-language
Model Card on HF 🤗: https://huggingface.co/txgsync/Qwen3.8-Flash-Next-MXFP4-MLX 

Qwen3.8 Flash Next MXFP4 MLX Parameters and Internals

LLM NameQwen3.8 Flash Next MXFP4 MLX
Repository 🤗https://huggingface.co/txgsync/Qwen3.8-Flash-Next-MXFP4-MLX 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size33.6b
Required VRAM99.7 GB
Updated2026-08-30
Maintainertxgsync
Model Typeqwen4_exp
Model Files  5.2 GB: 1-of-14   28.5 GB: 2-of-14   5.5 GB: 3-of-14   5.5 GB: 4-of-14   5.5 GB: 5-of-14   5.5 GB: 6-of-14   5.5 GB: 7-of-14   5.5 GB: 8-of-14   5.5 GB: 9-of-14   5.5 GB: 10-of-14   5.5 GB: 11-of-14   5.5 GB: 12-of-14   5.5 GB: 13-of-14   5.5 GB: 14-of-14   0.0 GB   0.0 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace