# mistralai/timestral

> A family of pretrained foundation models for multivariate probabilistic time series forecasting with covariate support. Enables zero-shot forecasting on CPU or GPU without training.

- Magnitude: 5.2 out of 10 — Early signal
- Stars: 88 total · +5 stars measured 2026-10-16, 00:05–01:30 UTC, ≈ 86 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-10-15 · Last push: 2026-10-15
- GitHub: https://github.com/mistralai/timestral · Page: https://gitnova.dev/en/r/mistralai/timestral

## Useful for

- Forecast sales from historical data with Timestral-209M
- Run zero-shot time series forecasting without training on your data
- Include known-future covariates (holidays, promotions) in demand forecasting

## Why it’s here

- Star-counter measurements on 2026-10-16 (UTC), 00:05–01:30: 83 → 88 stars (+5). This is the change over that interval.
- Estimated end-of-day forecast: about +86 stars, using observed gains and the previous day.
- The repository is 1 day old and already has 88 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #185.
- Hacker News: “Mistral Timestral” — 7 points, 9 h ago.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 4
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 87 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 4

## Stars per day, last 2 days (oldest → newest, today is partial)

2026-10-15 … 2026-10-16: 88, 5

## Hacker News

- Mistral Timestral — 7 points, 0 comments: https://news.ycombinator.com/item?id=50105524

## Spotted in now

- Top new repositories this week: #185

## More in this category

1. **chenglou/handwired** — 8.3 · Early signal · Language models · TypeScript · +52 stars measured 2026-10-16, 00:04–01:30 UTC, ≈ 937 by evening
   Turns regular JavaScript code into a differentiable neural net: if-else, loops and state are compiled into matrix multiplications and ReLU with no training. Runs on JS or WebGPU.
   Full card: https://gitnova.dev/en/r/chenglou/handwired.md
2. **lightseekorg/tokenspeed** — 6.3 · Breakout · Language models · Python · +26 stars measured 2026-10-16, 00:05–01:30 UTC, ≈ 262 by evening
   TokenSpeed is an open-source LLM inference engine for agentic workloads, combining TensorRT-LLM-level performance with vLLM-level usability. It separates a C++ control plane from a Python execution plane and ships a pluggable kernel…
   Full card: https://gitnova.dev/en/r/lightseekorg/tokenspeed.md
3. **Niko1221/Strata** — 4.3 · Cooling · Language models · C++ · +49 stars measured 2026-10-16, 00:06–01:31 UTC, ≈ 658 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md
4. **BaruqueRodrigues/llm-legislativo** — 4.3 · Early signal · Language models · Python · +6 stars measured 2026-10-16, 00:05–01:31 UTC, ≈ 48 by evening
   Large-scale Brazilian legislative corpus and a causal Transformer language model trained from scratch in pure PyTorch without pretrained weights or closed APIs.
   Full card: https://gitnova.dev/en/r/BaruqueRodrigues/llm-legislativo.md
5. **Fengzdadi/memory-bench-registry** — 4.0 · Early signal · Language models · HTML · +3 stars measured 2026-10-16, 00:07–01:31 UTC, ≈ 62 by evening
   A structured registry of agent memory benchmarks: one YAML file per benchmark, with every field traced back to its source (paper or official repository).
   Full card: https://gitnova.dev/en/r/Fengzdadi/memory-bench-registry.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-16 01:42 UTC, updated every 30 minutes.