LLM EXPLORER 65,695 MODELS INDEXED

Huihui Qwen3.6 35B A3B Abliterated 6bit XL MTP Mlx by leonsarmiento

By leonsarmiento · 547 downloads
HF Repo ↗ Copy URL

Huihui Qwen3.6 35B A3B Abliterated 6bit XL MTP Mlx is an open-source language model by leonsarmiento. Features: 35b LLM, VRAM: 30.5GB, Quantized.

  6-bit   6bit   Abliterated Base model:huihui-ai/huihui-qw... Base model:quantized:huihui-ai...   Basequant-xl   Conversational   Image-text-to-text   Mlx   Mlx-vlm   Moe   Mtp   Multimodal   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Vision
Model Card on HF 🤗: https://huggingface.co/leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-XL-MTP-mlx 

Huihui Qwen3.6 35B A3B Abliterated 6bit XL MTP Mlx Parameters and Internals

LLM NameHuihui Qwen3.6 35B A3B Abliterated 6bit XL MTP Mlx
Repository 🤗https://huggingface.co/leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-XL-MTP-mlx 
Base Model(s)  huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated   huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated
Model Size35b
Required VRAM30.5 GB
Updated2026-10-27
Maintainerleonsarmiento
Model Typeqwen3_5_moe
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   4.0 GB: 6-of-6
Quantization Type6bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Huihui Qwen3.6 35B A3B Abliterated 6bit XL MTP Mlx

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B MLX 4bit0K / 20.5 GB5131936
Qwen3.6 35B A3B MLX 6bit0K / 28.9 GB4785922
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB4735371
Qwen3.6 35B A3B UD MLX 4bit0K / 21.6 GB15720112
Qwen3.6 35B A3B MLX 4bit MTP0K / 20.5 GB9281
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB386241
Qwen3.6 35B A3B 2Bit GSQ0K / 13.5 GB21197
Qwen3.6 35B A3B OQ4e Fp16 Mtp0K / 22.4 GB1871
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Note: green Score (e.g. "73.2") means that the model is better than leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-XL-MTP-mlx.