What are the hardware requirements for Qwen3.6 35B A3B UD Q8 K XL Mlx?

Qwen3.6 35B A3B UD Q8 K XL Mlx requires approximately 38.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 35B A3B UD Q8 K XL Mlx and how large is it?

Qwen3.6 35B A3B UD Q8 K XL Mlx is developed by Brooooooklyn, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3.6 35B A3B UD Q8 K XL Mlx?

Qwen3.6 35B A3B UD Q8 K XL Mlx is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.6 35B A3B UD Q8 K XL Mlx by Brooooooklyn — VRAM 38.2GB

Name: Qwen3.6 35B A3B UD Q8 K XL Mlx
Author: Brooooooklyn

Qwen3.6 35B A3B UD Q8 K XL Mlx is an open-source language model by Brooooooklyn. Features: 35b LLM, VRAM: 38.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

8-bit Apple-silicon Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3... Conversational En Gated-delta-net Hybrid-attention Mlx Mlx-node Moe Q8 Quantized Qwen3.6 Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Unsloth-dynamic Zh

Model Card on HF 🤗: https://huggingface.co/Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx

Qwen3.6 35B A3B UD Q8 K XL Mlx Parameters and Internals

LLM Name	Qwen3.6 35B A3B UD Q8 K XL Mlx
Repository 🤗	https://huggingface.co/Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	38.2 GB
Updated	2026-09-11
Maintainer	Brooooooklyn
Model Type	qwen3_5_moe
Model Files	5.3 GB: 1-of-8 5.1 GB: 2-of-8 5.4 GB: 3-of-8 5.2 GB: 4-of-8 5.4 GB: 5-of-8 5.4 GB: 6-of-8 5.2 GB: 7-of-8 1.2 GB: 8-of-8
Supported Languages	en zh
Quantization Type	q8
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.6 35B A3B UD Q8 K XL Mlx capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Quantized Models of the Qwen3.6 35B A3B UD Q8 K XL Mlx

Model	Likes	Downloads	VRAM
Qwen3.6 35B Rust.mlx	10	386	37 GB

Best Alternatives to Qwen3.6 35B A3B UD Q8 K XL Mlx

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B MLX 4bit	0K / 20.5 GB	513193	6
Qwen3.6 35B A3B MLX 6bit	0K / 28.9 GB	478592	2
Qwen3.6 35B A3B MLX 8bit	0K / 37.8 GB	473537	1
Qwen3.6 35B A3B UD MLX 4bit	0K / 21.6 GB	15720	112
Qwen3.6 35B A3B OQ4e Fp16 Mtp	0K / 22.4 GB	187	1
Qwen3.6 35B A3B MLX 8bit	0K / 37.8 GB	3862	41
Qwen3.6 35B A3B 2Bit GSQ	0K / 13.5 GB	2119	7
Qwen3.6 35B A3B 6bit	0K / 28.9 GB	2742	8
Qwen3.6 35B A3B UD MLX 3bit	0K / 17.3 GB	2292	13
Nail Qwen3.6 35B A3B MLX 5bit	0K / 27.5 GB	83	1

Note: green Score (e.g. "73.2") means that the model is better than Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx.