Qwen3.6 35B A3B Abliterated Heretic MLX 4bit is an open-source language model by Youssofal. Features: 35b LLM, VRAM: 23.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.37.
4-bit 4bit Abliterated Apple-silicon Base model:quantized:youssofal... Base model:youssofal/qwen3.6-3... Conversational Heretic Mixture-of-experts Mlx Mlx-lm Moe Mpoa Quantized Qwen Qwen3.6 Qwen3 5 moe Region:us Safetensors Sharded Soma Tensorflow Uncensored
Model Card on HF 🤗: https://huggingface.co/Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-4bit
Qwen3.6 35B A3B Abliterated Heretic MLX 4bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen3.6 35B A3B Abliterated Heretic MLX 4bit Parameters and Internals
| LLM Name | Qwen3.6 35B A3B Abliterated Heretic MLX 4bit |
| Repository 🤗 | https://huggingface.co/Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-4bit |
| Base Model(s) | |
| Model Size | 35b |
| Required VRAM | 23.6 GB |
| Updated | 2026-04-17 |
| Maintainer | Youssofal |
| Model Type | qwen3_5_moe |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Qwen3_5MoeForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Transformers Version | 5.5.4 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Errors | replace |
Best Alternatives to Qwen3.6 35B A3B Abliterated Heretic MLX 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3.6 35B A3B 4bit DWQ | 0K / 20.7 GB | 14 | 5 |
| Qwen3.5 35B A3B UD Q4 K XL Mlx | 0K / 22.9 GB | 1352 | 5 |
| ...en3.5 35B A3B Abliterated 6bit | 0K / 28 GB | 2973 | 4 |
| Ecu Pilot Fp16 | 0K / 72.3 GB | 42 | 0 |
| Qwen3.6 35B A3B NVFP4 | 0K / 25.6 GB | 1223 | 4 |
| Darwin 35B A3B Opus Q8 GGUF | 0K / 10.7 GB | 825 | 13 |
| Qwen3.6 35B A3B RAM 25GB MLX | 0K / 26.4 GB | 20 | 2 |
| ...n3.5 35B A3B Abliterated Mxfp4 | 0K / 18.5 GB | 3155 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-4bit .
Rank the Qwen3.6 35B A3B Abliterated Heretic MLX 4bit 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! 🌟
What open-source LLMs or SLMs are you in search of? 52953 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a