What are the hardware requirements for Qwen3.5 122B A10B Bf16?

Qwen3.5 122B A10B Bf16 requires approximately 224.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 122B A10B Bf16 and how large is it?

Qwen3.5 122B A10B Bf16 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 Bf16?

Qwen3.5 122B A10B Bf16 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 Bf16 by mlx-community — VRAM 224.2GB

Name: Qwen3.5 122B A10B Bf16
Author: mlx-community

Qwen3.5 122B A10B Bf16 is an open-source language model by mlx-community. Features: 122b LLM, VRAM: 224.2GB, License: apache-2.0, LLM Explorer Score: 0.26.

Conversational Endpoints compatible Image-text-to-text Mlx Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-bf16

Qwen3.5 122B A10B Bf16 Parameters and Internals

LLM Name	Qwen3.5 122B A10B Bf16
Repository 🤗	https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-bf16
Model Size	122b
Required VRAM	224.2 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen3_5_moe
Model Files	4.2 GB: 1-of-49 5.0 GB: 2-of-49 5.0 GB: 3-of-49 5.0 GB: 4-of-49 5.0 GB: 5-of-49 5.0 GB: 6-of-49 5.0 GB: 7-of-49 5.0 GB: 8-of-49 5.0 GB: 9-of-49 5.0 GB: 10-of-49 5.0 GB: 11-of-49 5.0 GB: 12-of-49 5.0 GB: 13-of-49 5.0 GB: 14-of-49 5.0 GB: 15-of-49 5.0 GB: 16-of-49 5.0 GB: 17-of-49 5.0 GB: 18-of-49 5.0 GB: 19-of-49 5.0 GB: 20-of-49 5.0 GB: 21-of-49 5.0 GB: 22-of-49 5.0 GB: 23-of-49 5.0 GB: 24-of-49 5.0 GB: 25-of-49 5.0 GB: 26-of-49 5.0 GB: 27-of-49 5.0 GB: 28-of-49 5.0 GB: 29-of-49 5.0 GB: 30-of-49 5.0 GB: 31-of-49 5.0 GB: 32-of-49 5.0 GB: 33-of-49 5.0 GB: 34-of-49 5.0 GB: 35-of-49 5.0 GB: 36-of-49 5.0 GB: 37-of-49 5.0 GB: 38-of-49 5.0 GB: 39-of-49 5.0 GB: 40-of-49 5.0 GB: 41-of-49 5.0 GB: 42-of-49 5.0 GB: 43-of-49 5.0 GB: 44-of-49 5.0 GB: 45-of-49
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Transformers Version	4.57.0.dev0

Rank the Qwen3.5 122B A10B Bf16 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 Qwen3.5 122B A10B Bf16

Model	Likes	Downloads	VRAM
Qwen3.5 122B A10B OptiQ 2bit	4	1093	46 GB

Best Alternatives to Qwen3.5 122B A10B Bf16

Best Alternatives	Context / RAM	Downloads	Likes
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 Abliterated	0K / 248.6 GB	49	5
Qwen3.5 122B A10B FP8	0K / 126.3 GB	1271983	112
...en3.5 122B A10B Int4 AutoRound	0K / 72 GB	142311	45
Qwen3.5 122B A10B WMix48	0K / 73.2 GB	215	3
Qwen3.5 122B A10B WMix58	0K / 87.5 GB	214	3
Qwen3.5 122B A10B WMix68	0K / 102.1 GB	156	1
...2.6 Destill Healed Abliterated	0K / 245.1 GB	1143	15
Qwen3.5 122B A10B OQ4 Mtp	0K / 72.5 GB	925	3

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.5-122B-A10B-bf16.