cd /news/machine-learning/timestral-open-weight-timeseries-fou… · home › topics › machine-learning › article
[ARTICLE · art-151178] src=huggingface.co ↗ pub= topic=machine-learning verified=true sentiment=· neutral

Timestral open weight timeseries foundation models from Mistral

Mistral AI released the Timestral family of open-weight time series foundation models on Hugging Face for zero-shot probabilistic forecasting, in four sizes: Timestral-5M (5.21M parameters), Timestral-28M (27.8M), Timestral-123M (0.1B), and Timestral-209M (0.2B). The models were published under the mistralai organization and updated about 15 hours before the collection listing.

read1 min publishedOct 16, 2026
Timestral open weight timeseries foundation models from Mistral
Image: Hugging Face Blog

Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Hardware Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up mistralai 's Collections Mistral Medium 3.5 Timestral Voxtral Mistral Small 4 Ministral 3 Ministral 3 - Additional Checkpoints Mistral × MTNRA Devstral 2 Mistral Large 3 Speech Evals Timestral updated about 15 hours ago Time series foundation models for zero-shot probabilistic forecasting. Upvote 16 +6 Sort: Collection mistralai/Timestral-209M Time Series Forecasting • 0.2B • Updated about 15 hours ago • 11 • 35 mistralai/Timestral-123M Time Series Forecasting • 0.1B • Updated about 15 hours ago • 5 • 18 mistralai/Timestral-28M Time Series Forecasting • 27.8M • Updated about 15 hours ago • 5 • 14 mistralai/Timestral-5M Time Series Forecasting • 5.21M • Updated about 15 hours ago • 7 • 17 Upvote 16 +12 Sort: Collection Share collection View history Collection guide Browse collections

source & further reading
huggingface.co — original article Two models on one 8 GB GPU: making the LLM wait for the TTS after every sentence stopped my voice assistant from stuttering Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline Arabic (Egyptian dialect) veterinary diagnosis assistant: dialect -> clinical-English gap and low accuracy on real owner messages
── more in #machine-learning 4 stories · sorted by recency
── more on @mistral ai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/timestral-open-weigh…] indexed:0 read:1min 2026-10-16 · —