FinanceText

XuanYuan

A large Chinese model family for the financial industry: advice, document reading and long texts up to 8k-16k. Not investment advice: decisions are made by a specialist.

Developer
Du Xiaoman (Duxiaoman-DI), China
First release
Sep 2023
Latest release
Dec 2024
Sizes
6B – 176B
License
Commercial use with conditionsLlama 2 and Llama 3.1 licenses depending on the version
Russian
Not supported
Ready-made builds
8-bit, 4-bit
Running
On your own serverNeeds a GPU
Industries
Finance, Customer support, Documents and accounting
Deploy on your server Hugging Face GitHub

What it does

  • Answering customer questions about banking products
  • Working through long financial documents
  • An internal assistant for a finance company regulations

Where it is used

Banks and lendersInsuranceFinancial consulting

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Llama3.1-XuanYuan-FinX1-Preview
  2. Llama3-XuanYuan3-70B
  3. XuanYuan-6B и XuanYuan-13B
  4. XuanYuan2-70B
  5. XuanYuan-13B-Chat
  6. XuanYuan-70B и XuanYuan-176B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can XuanYuan be used in a commercial project?

With conditions. License: Llama 2 and Llama 3.1 licenses depending on the version. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does XuanYuan need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does XuanYuan support Russian?

No. The developer documentation lists the supported languages and Russian is not among them.

Where can I download XuanYuan and what does it cost?

The XuanYuan weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

FinanceFin-R1Shanghai University of Finance and Economics (SUFE) · ChinaCommercial use allowed

A reasoning model for financial tasks based on Qwen2.5-7B: calculations, report analysis, regulatory questions. Trained on Chinese and English data.

DetailsFinanceDISC-FinLLMFudan-DISC, Fudan University · ChinaCommercial use with conditions

A financial assistant made of several fine-tuned experts: advice, calculations, document reading and knowledge-base search. Not investment advice: decisions are made by a specialist.

DetailsFinanceFinMA (PIXIU)The Fin AI / ChanceFocus · international projectCommercial use with conditions

One of the first open model families for financial text: reading statements, news and questions about numbers. Not investment advice: decisions are made by a specialist.

Details

Source: huggingface.co/Duxiaoman-DI/Llama3.1-XuanYuan-FinX1-Preview. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.