LLM EXPLORER 59,805 MODELS INDEXED

Qwen3.5 35B A3B UD Q4 K XL Mlx by Brooooooklyn

By Brooooooklyn · 199 downloads
HF Repo ↗ Copy URL

Qwen3.5 35B A3B UD Q4 K XL Mlx is an open-source language model by Brooooooklyn. Features: 35b LLM, VRAM: 22.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

  3-bit   4-bit   Apple-silicon   Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-35b-a3...   Conversational   En   Gated-delta-net   Hybrid-attention   Mlx   Mlx-node   Moe   Q4   Quantized   Qwen3.5   Qwen3 5 moe   Region:us   Safetensors   Unsloth-dynamic   Zh
Model Card on HF 🤗: https://huggingface.co/Brooooooklyn/Qwen3.5-35B-A3B-UD-Q4_K_XL-mlx 

Qwen3.5 35B A3B UD Q4 K XL Mlx Parameters and Internals

LLM NameQwen3.5 35B A3B UD Q4 K XL Mlx
Repository 🤗https://huggingface.co/Brooooooklyn/Qwen3.5-35B-A3B-UD-Q4_K_XL-mlx 
Base Model(s)  Qwen/Qwen3.5-35B-A3B   Qwen/Qwen3.5-35B-A3B
Model Size35b
Required VRAM22.9 GB
Updated2026-08-30
MaintainerBrooooooklyn
Model Typeqwen3_5_moe
Model Files  22.9 GB
Supported Languagesen zh
Quantization Typeq4
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 35B A3B UD Q4 K XL 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 8bit0K / 37.8 GB386241
Nail Qwen3.6 35B A3B MLX 5bit0K / 27.5 GB831
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Qwen3.6 35B A3B 5bit0K / 24.7 GB16285
Ornith 1.5 35B A3B MLX 6bit0K / 28 GB342096
Note: green Score (e.g. "73.2") means that the model is better than Brooooooklyn/Qwen3.5-35B-A3B-UD-Q4_K_XL-mlx.