LLM EXPLORER 60,147 MODELS INDEXED

Qwen3.8 Flash Next MLX 2bit MTP by Vontra

By Vontra · 908 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next MLX 2bit MTP is an open-source language model by Vontra. Features: 29.3b LLM, VRAM: 80.1GB, License: other, Quantized, LLM Explorer Score: 0.32.

  2-bit   2bit   Apple-silicon Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Image-text-to-text   Mixture-of-experts   Mlx   Mlx-vlm   Mtp   Omlx   Quantized   Qwen   Qwen3.8   Qwen4-exp   Qwen4 exp   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Vision   Vision-language
Model Card on HF 🤗: https://huggingface.co/Vontra/Qwen3.8-Flash-Next-MLX-2bit-MTP 

Qwen3.8 Flash Next MLX 2bit MTP Parameters and Internals

LLM NameQwen3.8 Flash Next MLX 2bit MTP
Repository 🤗https://huggingface.co/Vontra/Qwen3.8-Flash-Next-MLX-2bit-MTP 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size29.3b
Required VRAM80.1 GB
Updated2026-09-01
MaintainerVontra
Model Typeqwen4_exp
Model Files  4.2 GB: 1-of-20   4.2 GB: 2-of-20   4.2 GB: 3-of-20   4.2 GB: 4-of-20   4.2 GB: 5-of-20   4.3 GB: 6-of-20   4.0 GB: 7-of-20   4.0 GB: 8-of-20   2.8 GB: 9-of-20   2.8 GB: 10-of-20   4.1 GB: 11-of-20   4.0 GB: 12-of-20   4.3 GB: 13-of-20   4.1 GB: 14-of-20   4.0 GB: 15-of-20   4.0 GB: 16-of-20   4.2 GB: 17-of-20   4.3 GB: 18-of-20   4.2 GB: 19-of-20   4.0 GB: 20-of-20
Quantization Type2bit
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 Flash Next MLX 2bit MTP

Best Alternatives
Context / RAM
Downloads
Likes
...wen3.8 Flash Next MLX 4bit MTP0K / 102.6 GB581