FinanceMath and reasoning

Fino1 / Fin-o1

Models that spell out their reasoning before answering financial questions with numbers and tables. Not investment advice: decisions are made by a specialist.

Developer
The Fin AI, international project
First release
Feb 2025
Latest release
May 2025
Sizes
8B и 14B
License
Commercial use with conditionsmixed: Fin-o1 (built on Qwen3) is Apache 2.0, the earlier Fino1 (built on Llama 3.1) uses the Llama 3.1 license
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Finance, Documents and accounting, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Calculation questions on statements with the working shown
  • Working through tasks with tables and numbers from documents
  • Checking calculations made by hand

Where it is used

Finance departmentsAudit and reportingTraining for finance staff

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. Fin-o1-8B и Fin-o1-14B
  2. Fino1-14B
  3. Fino1-8B

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 Fino1 / Fin-o1 be used in a commercial project?

With conditions. License: mixed: Fin-o1 (built on Qwen3) is Apache 2.0, the earlier Fino1 (built on Llama 3.1) uses the Llama 3.1 license. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Fino1 / Fin-o1 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 Fino1 / Fin-o1 support Russian?

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

Where can I download Fino1 / Fin-o1 and what does it cost?

The Fino1 / Fin-o1 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.

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.

DetailsFinanceXuanYuanDu Xiaoman (Duxiaoman-DI) · ChinaCommercial use with conditions

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.

Details

Source: huggingface.co/TheFinAI/Fin-o1-8B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.