LLM EXPLORER 58,975 MODELS INDEXED

Qwen3.8 27B Heretic Abliterated MLX 8bit by mlasli

By mlasli · 417 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B Heretic Abliterated MLX 8bit is an open-source language model by mlasli. Features: 27b LLM, VRAM: 28.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  8-bit   8bit   Abliterated   Apple-silicon Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Decensored   En   Heretic   Mlx   Quantization   Quantized   Qwen3   Qwen3.8   Qwen3 5   Region:us   Roleplay   Safetensors   Sharded   Tensorflow   Uncensored
Model Card on HF 🤗: https://huggingface.co/mlasli/Qwen3.8-27B-Heretic-Abliterated-MLX-8bit 

Qwen3.8 27B Heretic Abliterated MLX 8bit Parameters and Internals

LLM NameQwen3.8 27B Heretic Abliterated MLX 8bit
Repository 🤗https://huggingface.co/mlasli/Qwen3.8-27B-Heretic-Abliterated-MLX-8bit 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM28.4 GB
Updated2026-08-19
Maintainermlasli
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   1.9 GB: 6-of-6
Supported Languagesen
Quantization Type8bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.15.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B Heretic Abliterated MLX 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.8 27B 8bit0K / 29.4 GB1389233
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
Qwen3.8 27B OptiQ 4bit0K / 19.4 GB31899
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Note: green Score (e.g. "73.2") means that the model is better than mlasli/Qwen3.8-27B-Heretic-Abliterated-MLX-8bit.