What are the hardware requirements for XYZ Aquila Pro?

XYZ Aquila Pro requires approximately 225 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed XYZ Aquila Pro and how large is it?

XYZ Aquila Pro is developed by XYZAILab, a model with 397b 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 XYZ Aquila Pro?

XYZ Aquila Pro is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

XYZ Aquila Pro by XYZAILab — VRAM 225GB

Name: XYZ Aquila Pro
Author: XYZAILab

XYZ Aquila Pro is an open-source language model by XYZAILab. Features: 397b LLM, VRAM: 225GB, License: apache-2.0, LLM Explorer Score: 0.44.

Agentic-search Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-397b-a... Conversational Endpoints compatible Image-text-to-text Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/XYZAILab/XYZ-Aquila-pro

XYZ Aquila Pro Parameters and Internals

LLM Name	XYZ Aquila Pro
Repository 🤗	https://huggingface.co/XYZAILab/XYZ-Aquila-pro
Base Model(s)	Qwen/Qwen3.5-397B-A17B Qwen/Qwen3.5-397B-A17B
Model Size	397b
Required VRAM	225 GB
Updated	2026-08-08
Maintainer	XYZAILab
Model Type	qwen3_5_moe
Model Files	5.0 GB: 1-of-159 5.0 GB: 2-of-159 5.0 GB: 3-of-159 5.0 GB: 4-of-159 5.0 GB: 5-of-159 5.0 GB: 6-of-159 5.0 GB: 7-of-159 5.0 GB: 8-of-159 5.0 GB: 9-of-159 5.0 GB: 10-of-159 5.0 GB: 11-of-159 5.0 GB: 12-of-159 5.0 GB: 13-of-159 5.0 GB: 14-of-159 5.0 GB: 15-of-159 5.0 GB: 16-of-159 5.0 GB: 17-of-159 5.0 GB: 18-of-159 5.0 GB: 19-of-159 5.0 GB: 20-of-159 5.0 GB: 21-of-159 5.0 GB: 22-of-159 5.0 GB: 23-of-159 5.0 GB: 24-of-159 5.0 GB: 25-of-159 5.0 GB: 26-of-159 5.0 GB: 27-of-159 5.0 GB: 28-of-159 5.0 GB: 29-of-159 5.0 GB: 30-of-159 5.0 GB: 31-of-159 5.0 GB: 32-of-159 5.0 GB: 33-of-159 5.0 GB: 34-of-159 5.0 GB: 35-of-159 5.0 GB: 36-of-159 5.0 GB: 37-of-159 5.0 GB: 38-of-159 5.0 GB: 39-of-159 5.0 GB: 40-of-159 5.0 GB: 41-of-159 5.0 GB: 42-of-159 5.0 GB: 43-of-159 5.0 GB: 44-of-159 5.0 GB: 45-of-159
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Transformers Version	5.12.1

Rank the XYZ Aquila Pro 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 XYZ Aquila Pro

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 397B A17B NVFP4	0K / 251.1 GB	428565	102
Qwen3.5 397B A17B NVFP4 V2	0K / 243.5 GB	23781	5
Ornith 1.0 397B	0K / 288.5 GB	447	4
...7B A17B Heretic Int4 AutoRound	0K / 212.3 GB	4351	4
Qwen3.5 397B A17B Nvfp4	0K / 221.3 GB	166	5
Qwen3.5 REAP 212B A17B	0K / 150.8 GB	37	14
Qwen3.5 REAP 262B A17B	0K / 351.1 GB	18	9
Ornith 1.0 397B Mlx 8bit	0K / 208.8 GB	855	3
Qwen3.5 397B A17B GPTQ Int4	0K / 92.4 GB	22114	35

Note: green Score (e.g. "73.2") means that the model is better than XYZAILab/XYZ-Aquila-pro.