GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
fastino
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
fastino
Model Tree
Input Modalities
Output Modalities
Supported Functionality
The model targets financial document reasoning, numerical question answering over filings and tables, numeric span extraction, financial entity recognition, conversational analysis, and source-grounded financial research. The evaluation suite includes FinQA, TAT-QA, SEC-Num, FinEntity, BizFinBench, BigFinanceBench, ConvFinQA, and FiQA.
The published weights are BF16 and require about 66 GB before runtime overhead. An 80 GB or larger GPU, or tensor parallelism across multiple GPUs, is recommended.
bash
pip install "vllm==0.23.0"
python
from vllm import LLM, SamplingParamsmodel_id = "fastino/Fastino-Nemotron-3.5-Lightning-Finance"llm = LLM(model=model_id,trust_remote_code=True,dtype="bfloat16",max_model_len=4096,)outputs = llm.generate(["Check this financial calculation and explain the result: ..."],SamplingParams(temperature=0.0, max_tokens=512),)print(outputs[0].outputs[0].text)
The Fastino Fine-Tuning Agent autonomously built evaluation sets, curated data, explored training mixtures and hyperparameters, recovered failed experiments, evaluated transfer, and selected the final checkpoint.
The winning adapter was trained on 13,698 de-duplicated examples covering:
The final mix deliberately allocated substantial coverage to SEC-Num and BizFinBench while retaining FinQA, TAT-QA, FinEntity, and BigFinanceBench examples. It was trained from the base checkpoint for two epochs with LoRA rank 32, learning rate 1e-4, and sequence packing disabled. Exact duplicates were removed within each source before mixture construction. Evaluation examples and labels were excluded from training.
Base and fine-tuned scores below use the Nemotron-3.5-Lightning July 29 checkpoint, inputs, prompts, decoding settings, inference route, and evaluator for each row.
| Benchmark | Evaluation scope | Nemotron base | Fastino-Finance | Change |
|---|---|---|---|---|
| FinQA, execution accuracy | dev, n=883 | 15.86% | 59.23% | +43.37 pp |
| TAT-QA, F1 | dev, n=1,668 | 19.01 | 56.63 | +37.62 |
| SEC-Num | matched, n=992 | 79.74% | 87.60% | +7.86 pp |
Performance on related tasks the model was not explicitly trained for.
| Benchmark | Evaluation scope | Nemotron base | Fastino-Finance | Change |
|---|---|---|---|---|
| ConvFinQA | held-out, n=300 | 15.00% | 57.33% | +42.33 pp |
| FiQA, macro-F1 | held-out, n=1,058 | 35.09 | 41.48 | +6.39 |
The agent used development evaluations for experiment selection and a separately frozen held-out lane for final characterization. Score-bearing comparisons were accepted only when base and candidate shared the same examples, prompt construction, decoding parameters, serving route, evaluator identity, and aggregation. Training mixtures were hashed and de-duplicated, and benchmark evaluation rows were excluded from training.
This is a specialized model whose capabilities are best characterized by the tasks above. Performance outside these tasks has not been comprehensively evaluated. Outputs are not a substitute for professional financial advice; high-stakes use requires independent validation and qualified human oversight.
bibtex
@misc{atreja2026pioneeragentcontinualimprovement,title={Pioneer Agent: Continual Improvement of Small Language Models in Production},author={Dhruv Atreja and Julia White and Nikhil Nayak and Kelton Zhang and Henrijs Princis and George Hurn-Maloney and Ash Lewis and Urchade Zaratiana},year={2026},eprint={2604.09791},archivePrefix={arXiv},primaryClass={cs.AI},url={https://arxiv.org/abs/2604.09791},}
This model is licensed under the Apache License 2.0.
| FinEntity, macro-F1 | held-out, 3 runs of n=197 | 60.16 | 79.54 | +19.38 |
| BizFinBench, full 9-task macro | 690 rows | 49.65% | 57.46% | +7.81 pp |