LLM EXPLORER 60,147 MODELS INDEXED

Qwen3.8 Flash Next MLX 4bit by nopmobiel

By nopmobiel · 1386 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next MLX 4bit is an open-source language model by nopmobiel. Features: 29.7b LLM, VRAM: 103.7GB, License: other, Quantized, LLM Explorer Score: 0.33.

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

Qwen3.8 Flash Next MLX 4bit Parameters and Internals

LLM NameQwen3.8 Flash Next MLX 4bit
Repository 🤗https://huggingface.co/nopmobiel/Qwen3.8-Flash-Next-MLX-4bit 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size29.7b
Required VRAM103.7 GB
Updated2026-09-01
Maintainernopmobiel
Model Typeqwen4_exp
Model Files  5.4 GB: 1-of-20   5.3 GB: 2-of-20   5.2 GB: 3-of-20   5.2 GB: 4-of-20   5.2 GB: 5-of-20   5.2 GB: 6-of-20   5.0 GB: 7-of-20   5.4 GB: 8-of-20   5.3 GB: 9-of-20   5.4 GB: 10-of-20   5.4 GB: 11-of-20   5.3 GB: 12-of-20   5.4 GB: 13-of-20   5.4 GB: 14-of-20   5.3 GB: 15-of-20   5.4 GB: 16-of-20   5.4 GB: 17-of-20   5.3 GB: 18-of-20   5.4 GB: 19-of-20   2.8 GB: 20-of-20
Quantization Type4bit
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace