Instructions to use vanta-research/atom-80b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vanta-research/atom-80b with Transformers:

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

pipe = pipeline("text-generation", model="vanta-research/atom-80b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vanta-research/atom-80b")
model = AutoModelForCausalLM.from_pretrained("vanta-research/atom-80b")
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

vLLM

How to use vanta-research/atom-80b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vanta-research/atom-80b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vanta-research/atom-80b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vanta-research/atom-80b

SGLang

How to use vanta-research/atom-80b 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 "vanta-research/atom-80b" \
    --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": "vanta-research/atom-80b",
		"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 "vanta-research/atom-80b" \
        --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": "vanta-research/atom-80b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vanta-research/atom-80b with Docker Model Runner:
```
docker model run hf.co/vanta-research/atom-80b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

VANTA Research

Independent AI research lab building safe, resilient language models optimized for human-AI collaboration

Atom-80B

Overview

Atom-80B is a state-of-the-art language model fine-tuned on the Qwen3 80B Next base, optimized for high-fidelity reasoning, collaborative interaction, and cognitive extension. Atom-80B is designed to be friendly, enthusiastic, and collaboration-first.

This model is a continuation of Project Atom from VANTA Research, which aims to scale the Atom persona from 4B-400B+. This model is the 5th in the Project Atom series.

Key strengths:

Complex, multi-step reasoning
Collaborative task execution and agentic workflows
Stable, flavorful persona alignment
Optimized inference efficiency

Training and Data

Base Model

Qwen3 80B Next: A leading foundation model with robust multilingual and coding capabilities.

Fine-Tuning Datasets

Atom-80B was fine-tuned on the same high-quality datasets as the smaller Atom variants, including:

Collaborative exploration and brainstorming
Research synthesis and question formulation
Technical explanation at varying complexity levels
Lateral thinking and creative problem-solving
Empathetic and supportive dialogue patterns

Intended Use

Primary Applications

Collaborative Brainstorming: Generating diverse ideas and building iteratively on user suggestions
Research Assistance: Synthesizing information, identifying key arguments, and formulating research questions
Technical Explanation: Simplifying complex concepts across difficulty levels (including ELI5)
Code Discussion: Exploring implementation approaches, debugging strategies, and architectural decisions
Creative Problem-Solving: Encouraging unconventional approaches and lateral thinking

Out-of-Scope Use

This model shall not be used for:

High-stakes decision-making without human oversight
Medical, legal, or financial advice
Generation of harmful, biased, or misleading content
Applications requiring guaranteed factual accuracy

Usage

Installation

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("vanta-research/atom-80B", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("vanta-research/atom-80B")
inputs = tokenizer("Explain quantum computing like I'm 10.", return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Ethical Considerations

This model is designed to support exploration and learning, not to replace human judgment. Users should:

Verify factual claims against authoritative sources
Apply critical thinking to generated suggestions
Recognize the model's limitations in high-stakes scenarios
Be mindful of potential biases in outputs
Use responsibly in accordance with applicable laws and regulations

Citation

@misc{atom-80b,
  title={Atom-80B: A Collaborative Thought Partner},
  author={VANTA Research},
  year={2026},
  howpublished={https://huggingface.co/vanta-research/atom-80b}
}