LLM EXPLORER 61,652 MODELS INDEXED

Qwen3.6 27B UD Q3 K XL Mlx by Brooooooklyn

By Brooooooklyn · 174 downloads
HF Repo ↗ Copy URL

Qwen3.6 27B UD Q3 K XL Mlx is an open-source language model by Brooooooklyn. Features: 27b LLM, VRAM: 18.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

  3-bit   Apple-silicon   Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.6-27b   Conversational   En   Gated-delta-net   Hybrid-attention   Mlx   Mlx-node   Q3   Quantized   Qwen3.6   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Unsloth-dynamic   Zh
Model Card on HF 🤗: https://huggingface.co/Brooooooklyn/Qwen3.6-27B-UD-Q3_K_XL-mlx 

Qwen3.6 27B UD Q3 K XL Mlx Parameters and Internals

LLM NameQwen3.6 27B UD Q3 K XL Mlx
Repository 🤗https://huggingface.co/Brooooooklyn/Qwen3.6-27B-UD-Q3_K_XL-mlx 
Base Model(s)  Qwen/Qwen3.6-27B   Qwen/Qwen3.6-27B
Model Size27b
Required VRAM18.7 GB
Updated2026-09-20
MaintainerBrooooooklyn
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.4 GB: 3-of-4   2.6 GB: 4-of-4
Supported Languagesen zh
Quantization Typeq3
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 27B UD Q3 K XL Mlx

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 MLX 5bit0K / 19.5 GB46750442
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.8 27B 8bit0K / 29.4 GB1389233
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
...wift Qwen3.8 27B OQ4e Fp16 Mtp0K / 17.8 GB66310
Qwen3.8 27B MLX 8bit0K / 29.4 GB248117
Note: green Score (e.g. "73.2") means that the model is better than Brooooooklyn/Qwen3.6-27B-UD-Q3_K_XL-mlx.