What are the hardware requirements for Qwen3.5 122B A10B FP8?

Qwen3.5 122B A10B FP8 requires approximately 126.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 122B A10B FP8 and how large is it?

Qwen3.5 122B A10B FP8 is developed by Qwen, 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 FP8?

Qwen3.5 122B A10B FP8 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 FP8 by Qwen — VRAM 126.3GB

Name: Qwen3.5 122B A10B FP8
Author: Qwen

Qwen3.5 122B A10B FP8 is an open-source language model by Qwen. Features: 122b LLM, VRAM: 126.3GB, License: apache-2.0, LLM Explorer Score: 0.36.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-122b-a... Conversational Deploy:azure Endpoints compatible Fp8 Image-text-to-text Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3.5-122B-A10B-FP8

Qwen3.5 122B A10B FP8 Parameters and Internals

LLM Name	Qwen3.5 122B A10B FP8
Repository 🤗	https://huggingface.co/Qwen/Qwen3.5-122B-A10B-FP8
Base Model(s)	Qwen/Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B
Model Size	122b
Required VRAM	126.3 GB
Updated	2026-08-09
Maintainer	Qwen
Model Type	qwen3_5_moe
Model Files	3.2 GB: 1-of-39 3.2 GB: 2-of-39 3.2 GB: 3-of-39 3.2 GB: 4-of-39 3.2 GB: 5-of-39 3.2 GB: 6-of-39 3.2 GB: 7-of-39 3.2 GB: 8-of-39 3.2 GB: 9-of-39 3.2 GB: 10-of-39 3.2 GB: 11-of-39 3.2 GB: 12-of-39 3.2 GB: 13-of-39 3.2 GB: 14-of-39 3.2 GB: 15-of-39 3.2 GB: 16-of-39 3.2 GB: 17-of-39 3.2 GB: 18-of-39 3.2 GB: 19-of-39 3.2 GB: 20-of-39 3.2 GB: 21-of-39 3.2 GB: 22-of-39 3.2 GB: 23-of-39 3.2 GB: 24-of-39 3.2 GB: 25-of-39 3.2 GB: 26-of-39 3.2 GB: 27-of-39 3.2 GB: 28-of-39 3.2 GB: 29-of-39 3.2 GB: 30-of-39 3.2 GB: 31-of-39 3.2 GB: 32-of-39 3.2 GB: 33-of-39 3.2 GB: 34-of-39 3.2 GB: 35-of-39 3.2 GB: 36-of-39 4.7 GB: 37-of-39 3.6 GB: 38-of-39 2.8 GB: 39-of-39
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Transformers Version	4.57.0.dev0

Rank the Qwen3.5 122B A10B FP8 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 FP8

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
...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
Qwen3.5 122B A10B	0K / 248.6 GB	45	1

Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3.5-122B-A10B-FP8.