LLM EXPLORER 64,561 MODELS INDEXED

Qwen3.8 27B Mxfp8 Mlx by zherebetskyy

By zherebetskyy · 301 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B Mxfp8 Mlx is an open-source language model by zherebetskyy. Features: 27b LLM, VRAM: 28.7GB, License: apache-2.0, LLM Explorer Score: 0.27.

  8-bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   En   Image-text-to-text   Image-to-text   Low-precision   Mlx   Mxfp8   Quantization   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/zherebetskyy/Qwen3.8-27B-mxfp8-mlx 

Qwen3.8 27B Mxfp8 Mlx Parameters and Internals

LLM NameQwen3.8 27B Mxfp8 Mlx
Repository 🤗https://huggingface.co/zherebetskyy/Qwen3.8-27B-mxfp8-mlx 
Base Model(s)  Qwen/Qwen3.8-27B   mlx-community/Qwen3.8-27B-bf16   Qwen/Qwen3.8-27B   mlx-community/Qwen3.8-27B-bf16
Model Size27b
Required VRAM28.7 GB
Updated2026-08-16
Maintainerzherebetskyy
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-6   5.3 GB: 2-of-6   5.3 GB: 3-of-6   5.3 GB: 4-of-6   5.3 GB: 5-of-6   2.2 GB: 6-of-6
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B Mxfp8 Mlx

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB963
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB193142182
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B FP80K / 0.4 GB123157416
Note: green Score (e.g. "73.2") means that the model is better than zherebetskyy/Qwen3.8-27B-mxfp8-mlx.