LLM EXPLORER 59,598 MODELS INDEXED

SuperQwen3.8 27B Abliterated MLX 4bit by Jiunsong

By Jiunsong · 1664 downloads
HF Repo ↗ Copy URL

SuperQwen3.8 27B Abliterated MLX 4bit is an open-source language model by Jiunsong. Features: 27b LLM, VRAM: 16GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.42.

  4-bit   4bit   Abliterated   Apple-silicon Base model:jiunsong/superqwen3... Base model:quantized:jiunsong/...   Conversational   En   Image-text-to-text   Ko   Mlx   Mlx-lm   Multimodal   Obliteratus   Quantized   Qwen3.5   Qwen3.8   Qwen3 5   Reasoning   Region:us   Safetensors   Sharded   Supertune   Tensorflow   Tool-calling   Uncensored
Model Card on HF 🤗: https://huggingface.co/Jiunsong/SuperQwen3.8-27b-abliterated-MLX-4bit 

SuperQwen3.8 27B Abliterated MLX 4bit Parameters and Internals

LLM NameSuperQwen3.8 27B Abliterated MLX 4bit
Repository 🤗https://huggingface.co/Jiunsong/SuperQwen3.8-27b-abliterated-MLX-4bit 
Base Model(s)  Jiunsong/SuperQwen3.8-27b-abliterated   Jiunsong/SuperQwen3.8-27b-abliterated
Model Size27b
Required VRAM16 GB
Updated2026-08-26
MaintainerJiunsong
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   5.4 GB: 3-of-3
Supported Languagesen ko
Quantization Type4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to SuperQwen3.8 27B Abliterated MLX 4bit

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
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.8 27B MLX 4bit0K / 16 GB1971210
Qwen3.8 27B MLX 8bit0K / 29.4 GB248117
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 Jiunsong/SuperQwen3.8-27b-abliterated-MLX-4bit.