Skip to content
Other

CCNorton Coil Optimizer

magnetic coil optimizer for stellarators

2 min readupdated

This standalone ONNX model solves the magnetic coil optimization problem for fusion stellarators within the Proxima Fusion CoilStellaration benchmark. The architecture combines analytical methods, a neural prior, and an iterative Levenberg-Marquardt solver (a nonlinear optimization algorithm). The model achieves an overall score of 0.9937, outperforming the standard baseline. It is useful for researchers in plasma physics and controlled nuclear fusion.

Key features

  • Physics-in-the-Graph paradigm: a combination of a neural network, database search, and an analytical solver.
  • Compact size of just 48.78 MB with 4.3 million parameters and zero external data files.
  • Support for two tracks: fixed (fixed_shape) and variable (variable_shape) geometry.
  • High accuracy with a median score of 1.0000 on official eval instances.

What you can do

  • Run inference via the official CoilStellaration benchmark ONNX runner to calculate magnetic configurations.
  • Integrate the model into plasma configuration design and toroidal magnet optimization pipelines.
  • Explore the performance of the LM optimizer algorithm on custom tasks.

Example

The model takes plasma boundary geometry tensors as input (for example, boundary_r_cos and boundary_z_sin) along with requirement parameters, and outputs three-dimensional coil coordinates coil_x_n, coil_y_n, coil_z_n and current values currents in accordance with the leaderboard specification.

Read moreDetails
• Overall score: 0.9937 (+0.0135 over base baseline)
• Benchmark: Proxima Fusion CoilStellaration (v1.0)
• Format: ONNX (opset 20, IR 10, CPUExecutionProvider)
• Parameters: 48.78 MB, 4,348,180 parameters
• fixed_shape result: average score 0.9931 (latency 1.737 s)
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.6 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Oursdesvosges/coilstellaration-ccnorton-coil-optimizer
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Oursdesvosges/coilstellaration-ccnorton-coil-optimizer --local-dir ~/models/coilstellaration-ccnorton-coil-optimizer
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of coilstellaration-ccnorton-coil-optimizer (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

Oursdesvosges/coilstellaration-ccnorton-coil-optimizer
Author
Oursdesvosges
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments