LLM EXPLORER 60,645 MODELS INDEXED

Qwen3.8 Flash Next REAP 288 MLX Serve 4bit MTP by 30cmtonyfaker

By 30cmtonyfaker · 553 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next REAP 288 MLX Serve 4bit MTP is an open-source language model by 30cmtonyfaker. Features: 75.9b LLM, VRAM: 14.9GB, License: other, Quantized, LLM Explorer Score: 0.32.

  4-bit   4bit   Apple-silicon Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   En   Image-text-to-text   Mlx   Mlx-serve   Moe   Mtp   Quantized   Qwen   Qwen4 exp   Reap   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/30cmtonyfaker/Qwen3.8-Flash-Next-REAP-288-MLX-Serve-4bit-MTP 

Qwen3.8 Flash Next REAP 288 MLX Serve 4bit MTP Parameters and Internals

LLM NameQwen3.8 Flash Next REAP 288 MLX Serve 4bit MTP
Repository 🤗https://huggingface.co/30cmtonyfaker/Qwen3.8-Flash-Next-REAP-288-MLX-Serve-4bit-MTP 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size75.9b
Required VRAM14.9 GB
Updated2026-09-07
Maintainer30cmtonyfaker
Model Typeqwen4_exp
Model Files  0.5 GB: 1-of-131   0.5 GB: 2-of-131   0.3 GB: 3-of-131   0.5 GB: 4-of-131   0.3 GB: 5-of-131   0.0 GB: 37-of-131   0.5 GB: 38-of-131   0.3 GB: 39-of-131   0.5 GB: 40-of-131   0.3 GB: 41-of-131   0.5 GB: 42-of-131   0.3 GB: 43-of-131   0.5 GB: 44-of-131   0.3 GB: 45-of-131   0.5 GB: 46-of-131   0.3 GB: 47-of-131   0.5 GB: 48-of-131   0.3 GB: 49-of-131   0.5 GB: 50-of-131   0.3 GB: 51-of-131   0.5 GB: 52-of-131   0.3 GB: 53-of-131   0.5 GB: 54-of-131   0.3 GB: 55-of-131   0.5 GB: 56-of-131   0.3 GB: 57-of-131   0.5 GB: 58-of-131   0.3 GB: 59-of-131   0.0 GB: 60-of-131   0.5 GB: 61-of-131   0.3 GB: 62-of-131   0.5 GB: 63-of-131   0.3 GB: 64-of-131   0.5 GB: 65-of-131   0.3 GB: 66-of-131   0.5 GB: 67-of-131   0.3 GB: 68-of-131   0.5 GB: 69-of-131   0.3 GB: 70-of-131
Supported Languagesen zh
Quantization Type4bit
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.8.0.dev0