t0-alpha Q4_0, WebGPU

Q4_0-quantized weights for theforecastingcompany/t0-alpha, packaged for client-side browser forecasting via WASM + WebGPU.

Runs entirely in the browser, no server required. Probabilistic multi-horizon time-series forecasting, ~102M parameters, smallest/fastest quant in this release.

Try the demo โ†’

What you gain, what you lose

You trade a little accuracy for a much smaller file: 59 MB, 0.14x the F32 weights and about half of Q8_0, and the fastest browser forecast of the release (29.8 ms single signal, Apple M2). On the full 97-config GIFT-Eval protocol it costs +1.1% MASE and +0.6% CRPS against our own F32 control, and it lands within 1.3% of the published t0-alpha card. Per-forecast drift is looser than Q8_0 (see Benchmarks below); use Q8_0 when accuracy matters more than download size.

Files

File Size Description
t0-alpha-q4_0.gguf 58.6 MB Forecasting transformer weights (Q4_0 quantized)
config.json <1 KB Model architecture and quantile-level configuration

Usage

These weights are consumed by t0-web, a Rust/WASM forecasting engine: its own WGSL kernels on WebGPU, and Burn's ndarray backend on CPU.

await t0wasm.initBackend();
const modelBuf = await fetch('t0-alpha-q4_0.gguf').then(r => r.arrayBuffer());
const model = t0wasm.T0Wasm.load(new Uint8Array(modelBuf));

const context = series.slice(-512);
const quantiles = await model.forecast(context, 32);

Weights are fetched from this repo and cached by the browser.

Requirements

  • WebGPU when available (Chrome or Edge 113+, over HTTPS), otherwise CPU (WebAssembly)
  • ~59 MB download on first load (cached afterward)

Pipeline

Series โ†’ patches of 32 (96-vector each)
  โ†’ 24 transformer blocks [WASM, WebGPU] โ†’ time and group attention, embed 512
    โ†’ 32-step quantile decoder โ†’ 5 quantile levels
      โ†’ autoregressive rollout for longer horizons

Benchmarks

GIFT-Eval, full 97 configs, normalized to Seasonal Naive

variant MASE CRPS
Published t0-alpha card (F32) 0.7240 0.4941
Our F32 control 0.7255 0.4942
This Q4_0 0.7334 0.4973

Isolating quantization from any pipeline effect (Q4_0 vs our own F32 control): +1.1% MASE, +0.6% CRPS, at 0.14x the F32 file size.

Drift vs our own F32 reference (54 synthetic cases)

quant mean drift worst % point drift worst %
this Q4_0 3.11 8.42
our Q8_0 0.53 1.78
our reconstruction of the INT8 recipe from the t0-beta INT8 card (not the official export) 0.85 2.04

Browser latency (headless Chromium, Apple M2, single signal, context 512)

warm ms batch-24 ms/signal
Official ONNX WebGPU export 64.0 8.87
This file (Q4_0-resident WebGPU) 29.8 11.2

Single-call latency is 29.8 ms against 64.0 ms for the official ONNX export, each measured on its own page; batched throughput is 11.2 against 8.87 ms/signal. Both comparisons with the official ONNX export were measured against the t0-alpha-onnx-int8 revision 1c18a3e2, before its 2026-10-18 re-export.

These time the forecast call alone; the demo page shows the full round trip, about 40 ms on the same M2.

Model Details

  • Base model: theforecastingcompany/t0-alpha by The Forecasting Company
  • Architecture: Patch transformer, time and group attention
  • Parameters: ~102M
  • Quantization: Q4_0 for attention.wQKV.weight, attention.wO.weight, mlp.0.weight, mlp.2.weight per layer; norms, embeddings, biases, and the quantile head kept at f16
  • Quantile levels: 5 (0.1, 0.25, 0.5, 0.75, 0.9)
  • License: Apache-2.0 (same as original), see LICENSE and NOTICE

Quantization

Weights-only quantization using standard GGUF Q4_0 blocks (32 values per block, fp16 scale), in ggml-compatible layout, dequantized on-GPU inside the WGSL matmul with F32 compute. Exported from the F32 safetensors by t0-web's own packer. The F32 path itself matches the PyTorch reference to 1.2e-6 max-abs.

Citation

@article{meyer2026t0,
  title   = {$t_0$: A Time-Series Foundation Model for Forecasting with Context},
  author  = {Meyer, Lucas and Sole, Claudio and Xiang, Huikan and Li, Nicolas and Franceschino, Lucas and Quera-Bofarull, Arnau and Scholl, Maarten P. and Fainberg, Joachim and N{\'e}giar, Geoffrey},
  journal = {arXiv preprint arXiv:2609.24559},
  year    = {2026},
  url     = {https://arxiv.org/abs/2609.24559},
}

Disclaimer

This is an independent port by idle-intelligence, not affiliated with or endorsed by The Forecasting Company. Forecast values may differ slightly from the original PyTorch implementation due to quantization.

Downloads last month
102
GGUF
Model size
0.1B params
Architecture
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for idle-intelligence/t0-alpha-q4_0-webgpu

Quantized
(10)
this model

Paper for idle-intelligence/t0-alpha-q4_0-webgpu

Evaluation results

  • MASE on GIFT-Eval (97 configs, normalized to Seasonal Naive)
    self-reported
    0.733
  • CRPS on GIFT-Eval (97 configs, normalized to Seasonal Naive)
    self-reported
    0.497