Instructions to use marco-molinari/FinLM-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use marco-molinari/FinLM-Reasoning with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-31b-it-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "marco-molinari/FinLM-Reasoning")

Transformers

How to use marco-molinari/FinLM-Reasoning with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="marco-molinari/FinLM-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("marco-molinari/FinLM-Reasoning", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use marco-molinari/FinLM-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "marco-molinari/FinLM-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marco-molinari/FinLM-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/marco-molinari/FinLM-Reasoning

SGLang

How to use marco-molinari/FinLM-Reasoning with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "marco-molinari/FinLM-Reasoning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marco-molinari/FinLM-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "marco-molinari/FinLM-Reasoning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marco-molinari/FinLM-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use marco-molinari/FinLM-Reasoning with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for marco-molinari/FinLM-Reasoning to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for marco-molinari/FinLM-Reasoning to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for marco-molinari/FinLM-Reasoning to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="marco-molinari/FinLM-Reasoning",
    max_seq_length=2048,
)

Docker Model Runner
How to use marco-molinari/FinLM-Reasoning with Docker Model Runner:
```
docker model run hf.co/marco-molinari/FinLM-Reasoning
```

FinLM-Reasoning

FinLM-Reasoning is an open financial reasoning model built to bring frontier-level numerical finance performance to teams that need accuracy, transparency, and low inference cost.

Financial workflows are moving from keyword search and brittle pipelines to AI agents that can read filings, reason over tables, perform multi-step calculations, and answer domain-specific financial questions. FinLM-Reasoning is designed for that future: a finance-specialized reasoning model optimized for numerical QA, table reasoning, and calculation-heavy financial workflows.

Models

Model	Link	Best for
FinLM-31B	https://huggingface.co/marco-molinari/FinLM-31B	General financial NLP, financial QA, filing analysis, summarization, classification, and broad finance workflows
FinLM-Reasoning	https://huggingface.co/marco-molinari/FinLM-Reasoning	Numerical financial reasoning, table QA, multi-step calculations, FinQA, ConvFinQA, and TAT-QA-style tasks

Why FinLM-Reasoning

Frontier-level financial reasoning: FinLM-Reasoning reaches the top score on the FinTest numerical reasoning aggregate among evaluated models.
Built for calculation-heavy finance tasks: Optimized for numerical QA, table reasoning, financial statement analysis, and multi-step financial calculations.
GRPO-optimized checkpoint: FinLM-Reasoning is trained from FinLM-31B and further optimized for numerical financial reasoning with GRPO.
Open and practical: Designed to offer strong reasoning performance at materially lower inference cost than large closed-source frontier systems.
Multimodal-ready foundation: Built from a multimodal base model and validated on extractive QA over rendered SEC filings.

Headline results

Model	All FinTest tasks	Held-out tasks	Financial reasoning
FinLM-31B	52.79	65.94	65.00
FinLM-Reasoning	48.55	54.95	78.00
Gemma-4-31B base	43.79	46.44	41.33
GPT-5.5	52.31	54.24	66.78
Gemini 3 Flash	53.91	60.63	56.18
Claude Opus 4.7	55.97	59.91	72.80

Scores are percentages. Numerical reasoning aggregates FinQA, TAT-QA, and ConvFinQA.

When to use which model

Use FinLM-31B when you need the strongest general financial model across a wide range of tasks.

Use FinLM-Reasoning when your workload is calculation-heavy, such as financial table QA, multi-step numerical questions, or reasoning over earnings reports.

Example use cases

Financial table QA
Multi-step financial calculations
Numerical reasoning over earnings reports
Filing and earnings-call analysis
Financial question answering
KPI and metric extraction
Analyst workflow automation
Financial research assistants
Risk and compliance research workflows
Benchmarking financial AI systems

Responsible use

FinLM models are research and development tools. They should not be used as the sole basis for investment decisions, credit decisions, lending decisions, insurance decisions, legal conclusions, regulatory filings, fraud accusations, or consumer financial advice.

For production use, we recommend human review, audit logs, domain-specific evaluation, bias testing, and validation against authoritative financial sources.

Citation


@misc{finlm_suite_2026,
title = {The FinLM Suite: Pushing the Limits of Open Source Financial Language Modeling},
author = {Marco Molinari, Mateusz Mikolajczak, Luca Imeneo, Alvise Sembenico, Deasy Darlene Tunas, Saharsha Navani},
year = {2026},
}

Downloads last month: 21

Dataset used to train marco-molinari/FinLM-Reasoning

Evaluation results

All tasks on FinTest
self-reported

48.550
Held-out tasks on FinTest
self-reported

54.950
Numerical reasoning on FinTest
self-reported

78.000