FinanceText

FinGPT

An open set of lightweight add-ons for ordinary language models that work with financial texts and news. Not investment advice: decisions are made by a specialist.

Developer
AI4Finance Foundation, USA
First release
Oct 2023
Latest release
Oct 2024
Sizes
adapters for 6B - 20B base models
License
Commercial use with conditionsMIT on the adapters; the base models come with their own licenses (Llama, Qwen, ChatGLM and others)
Russian
Not stated
Running
On your own serverNeeds a GPU
Industries
Finance, Marketing and content, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Assessing the tone of financial news and reports
  • Tagging mentions of companies and instruments in text
  • Preparing digests from a stream of business news

Where it is used

Financial and investment firmsAnalytics departmentsBusiness media

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
no versions

Versions

  1. FinGPT multi-task для Llama 3 8B
  2. FinGPT-forecaster для SZ50
  3. FinGPT-sentiment для InternLM-20B
  4. FinGPT LoRA для Llama 2, Qwen, ChatGLM, Falcon, MPT, BLOOM

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.

Frequently asked questions

Can FinGPT be used in a commercial project?

With conditions. License: MIT on the adapters; the base models come with their own licenses (Llama, Qwen, ChatGLM and others). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does FinGPT 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 FinGPT support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download FinGPT and what does it cost?

The FinGPT 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

FinanceFinBERTProsus · NetherlandsCommercial use allowed

A classic model that determines the tone of financial news: positive, negative or neutral. English only, runs fast on a CPU.

DetailsFinanceFin-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.

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/FinGPT/fingpt-mt_llama3-8b_lora. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.