LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit   URL Share it on

  12101   

Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit is an open-source language model by mlx-community. Features: 35b LLM, VRAM: 37GB, Quantized, LLM Explorer Score: 0.36.

  8-bit   8bit   Conversational   En   Mlx   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit 

Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit Benchmarks

LLME Score: 0.36203
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit (mlx-community/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit)
🌟 Advertise your project 🚀

Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit Parameters and Internals

LLM NameHuihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit
Repository 🤗https://huggingface.co/mlx-community/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit 
Model Nameunsloth/Qwen3.6-35B-A3B
Model Size35b
Required VRAM37 GB
Updated2026-05-12
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-7   5.4 GB: 2-of-7   5.4 GB: 3-of-7   5.4 GB: 4-of-7   5.4 GB: 5-of-7   5.4 GB: 6-of-7   4.7 GB: 7-of-7
Supported Languagesen
Quantization Type8bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<|vision_pad|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Abliterated Heretic MLX 4bit0K / 23.6 GB1889115
Qwen3.6 35B Rust.mlx0K / 37.1 GB77679
Qwen3.6 35B A3B UD Q4 K XL Mlx0K / 22.7 GB76228
Qwen3.6 35B A3B OptiQ 4bit0K / 21 GB11752
Qwen3.5 35B A3B UD Q4 K XL Mlx0K / 22.9 GB10415
Qwen3.6 35B A3B UD Q8 K XL Mlx0K / 38.2 GB6280
...en3.5 35B A3B Abliterated 6bit0K / 28 GB7914
Qwen3.6 35B A3B 4bit DWQ0K / 20.7 GB145
Ecu Pilot Fp160K / 72.3 GB110
...B A3B PrismaQuant 4.75bit Vllm0K / 23.5 GB6518621
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit.

Rank the Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated Mlx 8bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53651 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer