Instructions to use esa-sceva/llama3-satcom-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use esa-sceva/llama3-satcom-70b with Transformers:

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

pipe = pipeline("text-generation", model="esa-sceva/llama3-satcom-70b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("esa-sceva/llama3-satcom-70b")
model = AutoModelForCausalLM.from_pretrained("esa-sceva/llama3-satcom-70b")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use esa-sceva/llama3-satcom-70b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "esa-sceva/llama3-satcom-70b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "esa-sceva/llama3-satcom-70b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/esa-sceva/llama3-satcom-70b

SGLang

How to use esa-sceva/llama3-satcom-70b 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 "esa-sceva/llama3-satcom-70b" \
    --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": "esa-sceva/llama3-satcom-70b",
		"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 "esa-sceva/llama3-satcom-70b" \
        --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": "esa-sceva/llama3-satcom-70b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use esa-sceva/llama3-satcom-70b with Docker Model Runner:
```
docker model run hf.co/esa-sceva/llama3-satcom-70b
```

LLama3 SatCom 70B

LLama3 SatCom 70B is a high-capacity fine-tuned Large Language Model (LLM) developed under the ESA ARTES programme as part of the SatcomLLM / SCEVA (SatCom Expert Virtual Assistant) project.
It represents the largest and most capable SatCom-specialised LLM, purpose-built to support satellite communications (SatCom) professionals through advanced reasoning, multi-step problem solving, and expert-level Q&A.

Model Description

Base model: meta-llama/Llama-3.3-70B-Instruct
Fine-tuning type: Instruction fine-tuning (IFT)
Training data: Curated and synthetic SatCom QA, including chain-of-thought annotated datasets
Architecture: Decoder-only transformer, 70 billion parameters
Languages: English
License: LLama-3.3 Community License Agreement

This large-scale variant extends the reasoning and factual accuracy of the 8B model, providing enhanced comprehension of technical systems, higher stability in multi-step mathematical reasoning, and greater contextual understanding across complex SatCom documents.
It excels in tasks such as link budget evaluation, propagation modeling, 5G/6G NTN design, and mission architecture analysis. Thanks to its larger parameter count and extended context window, it can process longer technical passages, integrate multiple data sources, and maintain coherence across complex analytical workflows.

Training Datasets

Dataset	Description
esa-sceva/satcom-synth-qa	Synthetic QA data generated with domain-validated prompts and expert-reviewed teacher models
esa-sceva/satcom-synth-qa-cot	Chain-of-thought annotated QA to strengthen reasoning accuracy and factual traceability

Intended Use

Primary use cases:

Advanced reasoning and Q&A for SatCom system design and analysis
Automated support for link budget calculations and RF engineering tasks
Conceptual guidance for 5G/6G NTN and inter-satellite network operations
Mission design evaluation and anomaly diagnosis assistance
Research, education, and technical documentation in satellite communications

Intended users:

ESA engineers and mission planners
SatCom and aerospace researchers
System architects and technical operators
Academic institutions and educational users

Limitations

The model does not access live telemetry or proprietary ESA mission data.
Generated answers should be validated by domain experts before operational use.
It is not suitable for safety-critical or real-time decision-making.
May produce confident but incorrect answers outside its domain

Technical Details

Parameter	Value
Base Model	Llama 3.3 70B Instruct
Parameters	70 billion
Context length	128k tokens
Precision	bfloat16 / fp16
Framework	Lit-GPT (Lightning AI)
Training infra	EuroHPC MareNostrum5 + AWS EC2
Optimisation	LoRA fine-tuning, cosine LR schedule

Evaluation

Evaluation Datasets

The model was evaluated across SatCom-specific and general-domain benchmarks, focusing on mathematical reasoning, conceptual understanding, and applied problem solving.

Dataset	Subset	Description
esa-sceva/satcom-qa	Open SatCom QA	Conceptual and reasoning-based questions on SatCom workflows, regulation, and mission/system design
	Math SatCom QA	Quantitative and multi-step engineering problems derived from orbital mechanics and RF analysis
esa-sceva/satcom-mcqa	Open MCQA	Conceptual multiple-choice questions on protocols, architectures, and communication systems
	Math MCQA	Numerical link-budget and propagation-focused multiple-choice problems

Results

Model	MCQA (Accuracy)			Satcom-QA			EVE-QA
Model	Satcom	EVE	TeleQnA	Norm.	Bin.	WR	Norm.	Bin.	WR
Llama-3.3-70B-Instruct	87.73	85.29	74.70	87.39	85.20	—	66.44	75.30	—
`llama3-satcom-70b`	88.08	86.62	75.03	90.84	86.80	51.01	69.01	76.40	51.22

Table: Evaluation results (%).

Norm. denotes the normalized score obtained by averaging 1–5 ratings from a panel of LLM judges (Qwen3, gpt-4.1-mini, Mistral-Large-2512, and DeepSeek-V3.2) and scaling to [0,1].
Bin. is the binary accuracy computed from correctness judgments.
WR (Adjusted Win Rate) is defined as (wins + 0.5 × ties) / total, based on pairwise comparisons with randomized answer order.
Multiple-choice performance is measured using standard accuracy.
All results are averaged over 3–5 runs; standard deviation ≤ 0.25 pp for open-ended QA and ≤ 0.10 pp for MCQA.

Summary

LLama3 SatCom 70B combines the linguistic precision of Llama 3.3 with domain-specialised fine-tuning from ESA’s SCEVA project, achieving great reasoning and analytical performance in satellite communications.
It represents a step toward intelligent, domain-grounded AI assistants capable of supporting complex engineering and research workflows across the space communications ecosystem.

Downloads last month: 164

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for esa-sceva/llama3-satcom-70b

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Finetuned

(614)

this model

Finetunes

1 model

esa-sceva
/

llama3-satcom-70b