Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

TinyCast: A 146K-Parameter Zero-Shot Forecaster That Runs on Embedded Devices

AI By Crimson AI Hugging Face Papers 22 August 2026 · 00:00 17 views
Share: X Telegram

Hugging Face researchers introduce TinyCast, an attention-free zero-shot forecaster with only 146,505 parameters that computes periodicity via spectral detection and runs end-to-end on a Cortex-M7 in 4.08 seconds, setting a new size-accuracy frontier.

TinyCast: A 146K-Parameter Zero-Shot Forecaster That Runs on Embedded Devices

Key points

Hugging Face researchers have unveiled TinyCast, a compact zero-shot time series forecaster that packs predictive power into just 146,505 parameters. The model is attention-free, relying on a zero-parameter spectral detector to compute dominant periods from the context, then folding the data on their phase before a dilated convolutional encoder and a block-autoregressive quantile decoder generate the forecast distribution.

This design philosophy — computing periodicity rather than learning it — allows TinyCast to be exceptionally small. It is the smallest model on the GIFT-Eval board with a public per-configuration result and no declared test-data leakage. Below 1.4 million parameters, it is the only zero-shot entry that emits a predictive distribution instead of mere point forecasts, and it defines the size-accuracy frontier on probabilistic accuracy.

Despite its size, TinyCast competes with much larger models. On Chronos-ZS and fev-bench, every neural model outperforming it carries at least 28 times its parameter count. Its efficiency stems from using only convolutions and matrix multiplications, enabling static INT8 export and full on-device forecasting without per-signal fitting.

In a demonstration of its embedded-device compatibility, TinyCast ran a complete forecast on a Cortex-M7 microcontroller in 4.08 seconds within 731 KB of RAM, at a cost of about 2% of point accuracy. The weights, code, and training recipe are publicly available, inviting further exploration and adoption.

Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4