LLM EXPLORER 59,962 MODELS INDEXED

Qwen3.8 Flash Next MLX OQ2 MTP by Vontra

By Vontra · 915 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next MLX OQ2 MTP is an open-source language model by Vontra. Features: 23.5b LLM, VRAM: 70.5GB, License: other, LLM Explorer Score: 0.34.

  2-bit   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   Oq   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-oQ2-MTP 

Qwen3.8 Flash Next MLX OQ2 MTP Parameters and Internals

LLM NameQwen3.8 Flash Next MLX OQ2 MTP
Repository 🤗https://huggingface.co/Vontra/Qwen3.8-Flash-Next-MLX-oQ2-MTP 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size23.5b
Required VRAM70.5 GB
Updated2026-08-30
MaintainerVontra
Model Typeqwen4_exp
Model Files  5.1 GB: 1-of-15   5.1 GB: 2-of-15   5.1 GB: 3-of-15   5.0 GB: 4-of-15   5.1 GB: 5-of-15   5.0 GB: 6-of-15   5.0 GB: 7-of-15   5.0 GB: 8-of-15   5.0 GB: 9-of-15   5.0 GB: 10-of-15   5.0 GB: 11-of-15   5.0 GB: 12-of-15   5.0 GB: 13-of-15   5.0 GB: 14-of-15   0.1 GB: 15-of-15
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace