LLM EXPLORER 58,608 MODELS INDEXED

Qwen3.8 27B MLX Mixed 6bit by TheCluster

By TheCluster · 150 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B MLX Mixed 6bit is an open-source language model by TheCluster. Features: 27b LLM, VRAM: 20.8GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.31.

  6-bit   6bit   Af   Ar Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   De   El   En   Es   Fa   Fi   Fr   He   Id   Image-text-to-text   Is   It   Ja   Ko   Mixed-precision   Mlx   Ms   Nl   Pa   Pl   Pt   Quantized   Qwen3 5   Region:us   Ru   Safetensors   Sharded   Sv   Sw   Tensorflow   Tr   Uk   Zh
Model Card on HF 🤗: https://huggingface.co/TheCluster/Qwen3.8-27B-MLX-mixed-6bit 

Qwen3.8 27B MLX Mixed 6bit Parameters and Internals

LLM NameQwen3.8 27B MLX Mixed 6bit
Repository 🤗https://huggingface.co/TheCluster/Qwen3.8-27B-MLX-mixed-6bit 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM20.8 GB
Updated2026-08-16
MaintainerTheCluster
Model Typeqwen3_5
Model Files  5.4 GB: 1-of-4   5.3 GB: 2-of-4   5.3 GB: 3-of-4   4.8 GB: 4-of-4
Supported Languagesen zh ru es fr it ja ko af de ar tr is pl sw sv nl he id uk fa pa pt ms fi el
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 MLX Mixed 6bit

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 TheCluster/Qwen3.8-27B-MLX-mixed-6bit.