What are the hardware requirements for Qwen3.5 122B A10B 8bit?

Qwen3.5 122B A10B 8bit requires approximately 129.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 122B A10B 8bit and how large is it?

Qwen3.5 122B A10B 8bit 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.

How does Qwen3.5 122B A10B 8bit perform on standard benchmarks?

Qwen3.5 122B A10B 8bit has the following published scores: LMSYS ELO 1417. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen3.5 122B A10B 8bit by mlx-community — VRAM 129.7GB

Name: Qwen3.5 122B A10B 8bit
Author: mlx-community

Qwen3.5 122B A10B 8bit is an open-source language model by mlx-community. Features: 122b LLM, VRAM: 129.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.41, ELO: 1417.

8-bit 8bit Conversational Endpoints compatible 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-8bit

Qwen3.5 122B A10B 8bit Benchmarks

LMSys ELO 1417 vs 1272 (so35) 11.4%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Qwen3.5 122B A10B 8bit Parameters and Internals

LLM Name	Qwen3.5 122B A10B 8bit
Repository 🤗	https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-8bit
Model Size	122b
Required VRAM	129.7 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen3_5_moe
Model Files	5.3 GB: 1-of-25 5.3 GB: 2-of-25 5.3 GB: 3-of-25 5.3 GB: 4-of-25 5.3 GB: 5-of-25 5.3 GB: 6-of-25 5.3 GB: 7-of-25 5.3 GB: 8-of-25 5.3 GB: 9-of-25 5.3 GB: 10-of-25 5.3 GB: 11-of-25 5.3 GB: 12-of-25 5.3 GB: 13-of-25 5.3 GB: 14-of-25 5.3 GB: 15-of-25 5.3 GB: 16-of-25 5.3 GB: 17-of-25 5.3 GB: 18-of-25 5.3 GB: 19-of-25 5.3 GB: 20-of-25 5.3 GB: 21-of-25 5.3 GB: 22-of-25 5.3 GB: 23-of-25 5.3 GB: 24-of-25 2.5 GB: 25-of-25
Quantization Type	8bit
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.5 122B A10B 8bit 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 8bit

Best Alternatives	Context / RAM	Downloads	Likes
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	359	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
Qwen3.5 122B A10B	0K / 248.6 GB	1680	8

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.5-122B-A10B-8bit.