What are the hardware requirements for Qwen3.5 122B A10B 6bit Gs32?

Qwen3.5 122B A10B 6bit Gs32 requires approximately 107.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 122B A10B 6bit Gs32 and how large is it?

Qwen3.5 122B A10B 6bit Gs32 is developed by mlx-community, a model with 122b 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 Qwen3.5 122B A10B 6bit Gs32?

Qwen3.5 122B A10B 6bit Gs32 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 122B A10B 6bit Gs32 by mlx-community — VRAM 107.9GB

Name: Qwen3.5 122B A10B 6bit Gs32
Author: mlx-community

Qwen3.5 122B A10B 6bit Gs32 is an open-source language model by mlx-community. Features: 122b LLM, VRAM: 107.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

6-bit 6bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-122b-a... Conversational Image-text-to-text Mlx Quantized Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-6bit-gs32

Qwen3.5 122B A10B 6bit Gs32 Parameters and Internals

LLM Name	Qwen3.5 122B A10B 6bit Gs32
Repository 🤗	https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-6bit-gs32
Base Model(s)	Qwen/Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B
Model Size	122b
Required VRAM	107.9 GB
Updated	2026-09-07
Maintainer	mlx-community
Model Type	qwen3_5_moe
Model Files	5.3 GB: 1-of-21 5.2 GB: 2-of-21 5.1 GB: 3-of-21 5.1 GB: 4-of-21 5.2 GB: 5-of-21 5.1 GB: 6-of-21 5.1 GB: 7-of-21 5.2 GB: 8-of-21 5.1 GB: 9-of-21 5.1 GB: 10-of-21 5.2 GB: 11-of-21 5.1 GB: 12-of-21 5.1 GB: 13-of-21 5.2 GB: 14-of-21 5.1 GB: 15-of-21 5.1 GB: 16-of-21 5.2 GB: 17-of-21 5.1 GB: 18-of-21 5.1 GB: 19-of-21 5.2 GB: 20-of-21 5.0 GB: 21-of-21
Quantization Type	6bit
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.5 122B A10B 6bit Gs32 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

Best Alternatives to Qwen3.5 122B A10B 6bit Gs32

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 122B A10B 8bit	0K / 129.7 GB	4124	2
Qwen3.5 122B A10B 4bit	0K / 69.5 GB	14412	19
Qwen3.5 122B A10B OptiQ 2bit	0K / 46.1 GB	1093	4
Qwen3.5 122B A10B 6bit	0K / 100.1 GB	3846	3
...3.5 122B A10B GameDev MLX 4bit	0K / 44.4 GB	249	4
Qwen3.5 122B A10B 5bit	0K / 85.2 GB	654	2
...22B A10B Vision MLX Mixed 4bit	0K / 4.7 GB	44	0
Qwen3.5 122B A10B NVFP4	0K / 83.5 GB	248732	49
Qwen3.5 122B A10B	0K / 248.6 GB	2139628	605
Qwen3.5 122B A10B	0K / 248.6 GB	45	1

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.5-122B-A10B-6bit-gs32.