LLM EXPLORER 58,608 MODELS INDEXED

Qwen3.8 27B 6bit Mlx by zherebetskyy

By zherebetskyy · 337 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B 6bit Mlx is an open-source language model by zherebetskyy. Features: 27b LLM, VRAM: 22.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  27b   6-bit   6bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Image-text-to-text   Image-to-text   Mlx   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/zherebetskyy/Qwen3.8-27B-6bit-mlx 

Qwen3.8 27B 6bit Mlx Parameters and Internals

LLM NameQwen3.8 27B 6bit Mlx
Repository 🤗https://huggingface.co/zherebetskyy/Qwen3.8-27B-6bit-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 VRAM22.7 GB
Updated2026-08-16
Maintainerzherebetskyy
Model Typeqwen3_5
Model Files  5.4 GB: 1-of-5   5.3 GB: 2-of-5   5.3 GB: 3-of-5   5.3 GB: 4-of-5   1.4 GB: 5-of-5
Quantization Type6bit
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 6bit Mlx

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Qwen3.8 27B 8bit0K / 29.4 GB1389233
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.8 27B 4bit0K / 16 GB605527
Qwen3.8 27B MLX 4bit0K / 16 GB1971210
Qwen3.8 27B MLX 8bit0K / 29.4 GB248117
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
Note: green Score (e.g. "73.2") means that the model is better than zherebetskyy/Qwen3.8-27B-6bit-mlx.