Instructions to use ParallaxOpen/Vela-Lumen-15M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ParallaxOpen/Vela-Lumen-15M with Transformers:

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

pipe = pipeline("text-generation", model="ParallaxOpen/Vela-Lumen-15M")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ParallaxOpen/Vela-Lumen-15M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ParallaxOpen/Vela-Lumen-15M with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ParallaxOpen/Vela-Lumen-15M:F16
# Run inference directly in the terminal:
llama cli -hf ParallaxOpen/Vela-Lumen-15M:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ParallaxOpen/Vela-Lumen-15M:F16
# Run inference directly in the terminal:
llama cli -hf ParallaxOpen/Vela-Lumen-15M:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ParallaxOpen/Vela-Lumen-15M:F16
# Run inference directly in the terminal:
./llama-cli -hf ParallaxOpen/Vela-Lumen-15M:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ParallaxOpen/Vela-Lumen-15M:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ParallaxOpen/Vela-Lumen-15M:F16

Use Docker

docker model run hf.co/ParallaxOpen/Vela-Lumen-15M:F16

LM Studio
Jan

vLLM

How to use ParallaxOpen/Vela-Lumen-15M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ParallaxOpen/Vela-Lumen-15M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ParallaxOpen/Vela-Lumen-15M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ParallaxOpen/Vela-Lumen-15M:F16

SGLang

How to use ParallaxOpen/Vela-Lumen-15M 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 "ParallaxOpen/Vela-Lumen-15M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ParallaxOpen/Vela-Lumen-15M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ParallaxOpen/Vela-Lumen-15M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ParallaxOpen/Vela-Lumen-15M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use ParallaxOpen/Vela-Lumen-15M with Ollama:
```
ollama run hf.co/ParallaxOpen/Vela-Lumen-15M:F16
```
Unsloth Desktop
Docker Model Runner
How to use ParallaxOpen/Vela-Lumen-15M with Docker Model Runner:
```
docker model run hf.co/ParallaxOpen/Vela-Lumen-15M:F16
```

Lemonade

How to use ParallaxOpen/Vela-Lumen-15M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ParallaxOpen/Vela-Lumen-15M:F16

Run and chat with the model

lemonade run user.Vela-Lumen-15M-F16

List all available models

lemonade list

Atomic Chat

Vela 15M Preview

A 15M-parameter math content generator trained from scratch on a single 8GB laptop GPU.

Preview: This is an early version. More training data and better results coming soon.

Downloads

Format	File	Size	How to Use
GGUF F16	`vela-lumen-15m-f16.gguf`	59 MB	Works with Ollama, llama.cpp, LM Studio
Safetensors FP16	`model-fp16.safetensors`	44 MB	Half precision, Python
Safetensors FP32	`model.safetensors`	89 MB	Full precision, training

Quick Start (Ollama)

wget https://huggingface.co/ParallaxOpen/Vela-Lumen-15M/resolve/main/vela-lumen-15m-f16.gguf
cat > Modelfile << EOF
FROM vela-lumen-15m-f16.gguf
TEMPLATE "{{ .System }}{{ .Prompt }}"
SYSTEM "You are a math tutor."
EOF
ollama create vela-15m-preview -f Modelfile
ollama run vela-15m-preview

What It Does

Math Content Generation:

Generates math word problems and equations
Generates homework-style questions
Generates math explanations and tutorials
Generates LaTeX formulas

Example:

Prompt: "Create a math problem about:"
Output: "The expression (x/m * x) - (x/m * x) = x.
        Recall that (x/m * x) - (x/m * x) = x.
        Therefore, we can solve for..."

ELO Rating

Metric	Value
Estimated ELO	~800-850
GSM8K	0%
Params	15.5M

Comparison

Model	Params	GSM8K	ELO
Claude Fable 5	Unknown	Unknown	1507
Llama 3.2 1B	1.26B	7.6%	1111
SmolLM2-135M	135M	1.4%	N/A
Vela 15M Preview	15.5M	0%	~800-850

Model Details

Property	Value
Developer	ParallaxOpen
Parameters	15,486,080
Architecture	Transformer Decoder, GQA 4:2, SwiGLU, RMSNorm, RoPE
Context	512 tokens
Vocab	24,189
License	CC BY-NC 4.0

Training

Pretrain: 7B tokens, 200K steps, loss 2.5, ~10h on RTX 5060
SFT: 14K math samples, 5K steps, loss 3.32, ~30min on RTX 5060
Total: ~10 hours on a single 8GB laptop GPU

What's Next

More pretrain data (FineMath 50B tokens)
Better SFT with distilled data
Larger model (50M+ params)
Improved math reasoning

Citation

@software{vela-15m-preview,
  title={Vela 15M Preview: A 15M-param Math Content Generator},
  author={ParallaxOpen},
  year={2026},
  note={Preview version - trained on a single RTX 5060 Laptop GPU}
}

Downloads last month: -

Safetensors

Model size

23.2M params

Tensor type

F32