Instructions to use fastino/Fastino-Nemotron-3.5-Lightning-Healthcare with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fastino/Fastino-Nemotron-3.5-Lightning-Healthcare with Transformers:

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

pipe = pipeline("text-generation", model="fastino/Fastino-Nemotron-3.5-Lightning-Healthcare", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fastino/Fastino-Nemotron-3.5-Lightning-Healthcare", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("fastino/Fastino-Nemotron-3.5-Lightning-Healthcare", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fastino/Fastino-Nemotron-3.5-Lightning-Healthcare with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fastino/Fastino-Nemotron-3.5-Lightning-Healthcare"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fastino/Fastino-Nemotron-3.5-Lightning-Healthcare",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fastino/Fastino-Nemotron-3.5-Lightning-Healthcare

SGLang

How to use fastino/Fastino-Nemotron-3.5-Lightning-Healthcare 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 "fastino/Fastino-Nemotron-3.5-Lightning-Healthcare" \
    --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": "fastino/Fastino-Nemotron-3.5-Lightning-Healthcare",
		"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 "fastino/Fastino-Nemotron-3.5-Lightning-Healthcare" \
        --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": "fastino/Fastino-Nemotron-3.5-Lightning-Healthcare",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fastino/Fastino-Nemotron-3.5-Lightning-Healthcare with Docker Model Runner:
```
docker model run hf.co/fastino/Fastino-Nemotron-3.5-Lightning-Healthcare
```

Fastino Nemotron 3.5 Lightning Healthcare

Fastino-Nemotron-3.5-Lightning-Healthcare is a 30B-parameter, 3B-active mixture-of-experts model specialized for healthcare and biomedical applications. The repository contains a ready-to-run merged checkpoint: the NVIDIA Nemotron 3.5 Lightning checkpoint released July 29, 2026 plus Fastino's winning combined-healthcare E17b adapter. Users do not need to obtain or attach a separate LoRA.

Developed by: Fastino Labs, in collaboration with NVIDIA
Base checkpoint: NVIDIA Nemotron 3.5 Lightning, July 29, 2026 release
Post-training checkpoint: Fastino-Healthcare
License: Apache 2.0
Language: English
Modalities: Text
Model Release Blog: Release Blog
Fine-Tuning Agent: Private Preview
Research: Fastino Fine-Tuning Agent

What it is designed for

The model targets clinical and health conversation, biomedical question answering, clinical calculation, medical error detection and correction, biomedical concept extraction, clinical note summarization, and tool-using clinical administration and medical-agent tasks.

Quickstart

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.

pip install "vllm==0.23.0"

from vllm import LLM, SamplingParams

model_id = "fastino/Fastino-Nemotron-3.5-Lightning-Healthcare"

llm = LLM(
    model=model_id,
    trust_remote_code=True,
    dtype="bfloat16",
    max_model_len=4096,
)

clinical_note = """65-year-old male with history of hypertension, type 2
diabetes, and CKD stage 3 presents with 2 weeks of progressive dyspnea on
exertion and orthopnea. Exam: bibasilar crackles, 3+ pitting edema to knees,
BP 152/94. Meds: lisinopril 20 mg daily, furosemide 40 mg daily. CXR:
cardiomegaly with pulmonary congestion. Assessment: acute decompensated
heart failure."""

messages = [
    {
        "role": "system",
        "content": "You are a clinical documentation assistant. Summarize notes accurately and concisely. Do not add information that is not in the note.",
    },
    {
        "role": "user",
        "content": f"Summarize the following clinical note in 3-5 bullet points:\n\n{clinical_note}",
    },
]

outputs = llm.chat(
    messages,
    SamplingParams(temperature=0.0, max_tokens=512),
)
print(outputs[0].outputs[0].text)

Post-training recipe

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 72,358 de-duplicated examples covering:

general healthcare instruction following and physician-style health conversations;
biomedical question answering and clinical calculation;
medical error detection and correction;
clinical dialogue summarization and note generation;
biomedical concept, chemical, and disease extraction;
clinical administration and browser-based tool-use trajectories; and
medical-agent task trajectories.

The final balanced mixture modestly upweighted difficult HealthBench-style examples while preserving broad healthcare, biomedical extraction, and newer agent-task coverage. It was trained from the base checkpoint for two epochs with LoRA rank 64, learning rate 1.5e-4, batch size 32, and sequence packing disabled. Evaluation, development, and blind rows and their labels were excluded from training.

Benchmark evaluation

Base and fine-tuned scores below use the same July 29 checkpoint, inputs, prompts, decoding settings, inference route, and evaluator for each row.

In-domain benchmarks

Benchmark	Evaluation scope	July 29 base	Fastino-Healthcare	Change
HealthBench Pro	blind, n=180	26.83%	32.64%	+5.80 pp
HealthAdminBench	blind	25.67%	29.95%	+4.28 pp
MedAgent public v1/v2, Overall SR	blind, n=150	36.00%	40.00%	+4.00 pp
HealthBench Core	blind, n=700	49.67%	56.21%	+6.54 pp
PubMedQA	matched, n=500	59.00%	65.00%	+6.00 pp
MedCalc	matched, n=275	49.09%	54.18%	+5.09 pp
MEDEC, flag accuracy	matched, n=574	53.66%	64.98%	+11.32 pp
MEDEC, sentence accuracy	matched, n=574	48.08%	62.89%	+14.81 pp
MedMentions ST21pv	matched, n=878	19.74%	40.30%	+20.55 pp
BC5CDR	matched, n=500	47.92%	72.51%	+24.59 pp

HealthAdminBench used Task Description plus Portal Guidance with the accessibility-tree observation mode. MedAgent reports Overall Success Rate. MEDEC flag and sentence accuracy are reported separately.

Transfer to unseen benchmarks

Performance on related tasks the model was not explicitly trained for.

Benchmark	Evaluation scope	July 29 base	Fastino-Healthcare	Change
EkaCare	transfer, n=1,066	12.95%	32.83%	+19.88 pp
BC5CDR to BioRED	transfer, n=66	25.92%	41.77%	+15.85 pp

Evaluation protocol

The agent used development evaluations for experiment selection and a separately frozen blind 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 benchmark evaluation rows were excluded from training.

Limitations

This is a specialized research model, not a medical device. Its outputs are not a substitute for professional clinical judgment. Clinical or other high-stakes deployment requires independent validation, appropriate safeguards, and qualified human oversight.

Citation

@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},
}

License

This model is licensed under the Apache License 2.0.

Paper for fastino/Fastino-Nemotron-3.5-Lightning-Healthcare

Pioneer Agent: Continual Improvement of Small Language Models in Production

Paper • 2604.09791 • Published Apr 10 • 14

fastino
/

Fastino-Nemotron-3.5-Lightning-Healthcare