---
license: agpl-3.0
language:
- en
base_model: UofTCSSLab/Maia3-79M
base_model_relation: quantized
tags:
- chess
- maia
- maia3
- chessformer
- move-prediction
- onnx
- onnxruntime-web
- webgpu
- fp16
---

# Maia3 ONNX (fp16 + fp32)

Browser-ready **ONNX** exports of the [**Maia3**](https://huggingface.co/collections/UofTCSSLab/maia3)
family of transformer models for human chess move prediction. Each of the four
size variants is provided in **fp16** (half-precision weights, the headline
quantized artifact) and **fp32** (full precision).

These are conversions of the original PyTorch checkpoints — same weights, same
predictions — repackaged so they run client-side with
[`onnxruntime-web`](https://onnxruntime.ai/docs/tutorials/web/) (wasm or WebGPU)
without a Python/PyTorch backend.

For the architecture, training recipe, and evaluation see the paper
[*Chessformer: A Unified Architecture for Chess Modeling*](https://openreview.net/forum?id=2ltBRzEHyd)
(ICLR 2026).

## Files

| Variant | Params | Base model | `fp16` | `fp32` |
|---------|-------:|------------|-------:|-------:|
| 3M  | 3.2M  | [Maia3-ablate-3M](https://huggingface.co/UofTCSSLab/Maia3-ablate-3M) | `maia3-3m-ablation.fp16.onnx` (6.7 MB) | `maia3-3m-ablation.fp32.onnx` (12.8 MB) |
| 5M  | 5.2M  | [Maia3-5M](https://huggingface.co/UofTCSSLab/Maia3-5M)   | `maia3-5m.fp16.onnx` (10.8 MB) | `maia3-5m.fp32.onnx` (21.0 MB) |
| 23M | 22.9M | [Maia3-23M](https://huggingface.co/UofTCSSLab/Maia3-23M) | `maia3-23m.fp16.onnx` (45.8 MB) | `maia3-23m.fp32.onnx` (91.0 MB) |
| 79M | 78.9M | [Maia3-79M](https://huggingface.co/UofTCSSLab/Maia3-79M) | `maia3-79m.fp16.onnx` (156.1 MB) | `maia3-79m.fp32.onnx` (311.7 MB) |

The **fp16** files store weights in float16 (≈half the size) while keeping
float32 inputs/outputs, so they are numerically robust and a drop-in replacement
for the float32 graph.

## I/O contract

All models share one simplified signature:

```
inputs:
  tokens    float32 [batch, 64, 12]   # current board only, piece-only one-hot channels
  elo_self  float32 [batch]           # rating of the side to move
  elo_oppo  float32 [batch]           # rating of the opponent
outputs:
  logits_move   float32 [batch, 4352] # move policy over the Maia3 move vocabulary
  logits_value  float32 [batch, 3]    # [loss, draw, win] logits for the side to move
```

Positions are tokenized exactly as in the upstream Maia3 code (board mirrored when
Black is to move; move vocabulary of 4352 with 256 promotion entries). The single
64×12 board is replicated across the model's 8-position history internally, and the
ponder/timing head is dropped — matching the analysis export used by the Maia
platform frontend.

## Accuracy

Max per-position error of the **fp16** ONNX vs. the original **fp32** PyTorch
checkpoint (the fp32 ONNX matches PyTorch to ~1e-7):

| Variant | move-prob error | value-prob error |
|---------|----------------:|-----------------:|
| 3M  | 1.3e-4 | 2.8e-4 |
| 5M  | 1.7e-4 | 1.2e-4 |
| 23M | 6.9e-5 | 5.4e-4 |
| 79M | 9.6e-5 | 2.7e-4 |

## Usage (onnxruntime-web)

```js
import * as ort from 'onnxruntime-web'

// Load a variant (fp16 recommended for the browser)
const session = await ort.InferenceSession.create('maia3-79m.fp16.onnx', {
  graphOptimizationLevel: 'basic',     // see note below
  executionProviders: ['webgpu'],      // or ['wasm']
})

// tokens: Float32Array of length batch*64*12, elos: Float32Array length batch
const feeds = {
  tokens:   new ort.Tensor('float32', tokens,   [batch, 64, 12]),
  elo_self: new ort.Tensor('float32', eloSelf,  [batch]),
  elo_oppo: new ort.Tensor('float32', eloOppo,  [batch]),
}
const { logits_move, logits_value } = await session.run(feeds)
```

**Optimization level:** set `graphOptimizationLevel: 'basic'`. ORT's aggressive
`all`/`extended` CPU fusions hit a known `SimplifiedLayerNormFusion` bug on fp16
cast boundaries in this graph; `basic` loads cleanly across ORT versions and is
what the browser runtime effectively uses.

## Conversion

Exported with PyTorch's ONNX exporter at **opset 17**, basic graph optimization
(constant folding + LayerNorm fusion, all default-domain ops), then weights
converted to float16 with float32 I/O preserved (`keep_io_types`). `RMSNorm` was
decomposed into opset-17 primitives prior to export.

## License

AGPLv3, inherited from the upstream Maia3 checkpoints.

## Citation

```bibtex
@inproceedings{monroe2026chessformer,
  title={Chessformer: A Unified Architecture for Chess Modeling},
  author={Daniel Monroe and George Eilender and Philip Chalmers and Zhenwei Tang and Ashton Anderson},
  booktitle={The Fourteenth International Conference on Learning Representations},
  year={2026},
  url={https://openreview.net/forum?id=2ltBRzEHyd}
}
```