Marketplace · 60+ models
Data Analytics Decisions on top of data
Predictive analytics, forecasting, anomaly detection, time series analysis, and business intelligence accelerators — battle-tested on tabular and temporal data.
Editor's pick
The data analytics model most teams reach for first.
TimesFM
Decoder-only foundation model for zero-shot time series forecasting.
Spec sheet
- Family
- Google Research
- Parameters
- 200M
- License
- Apache 2.0
- Status
- Live
- Best for
- Decisions on top of data
- Sits in
- Data Analytics
Pricing and routing rank visible on InferenceBench. Variants and quantisations appear in the Yobibyte deploy console.
The rest of the lineup
5 more in Data Analytics. All deployable in one click.
Interpretable attention-based forecasting on multi-horizon, multi-variate inputs.
In-context tabular classifier that beats tuned XGBoost on small datasets.
Gradient boosting baseline — still the default winner on tabular data.
Self-attention model for unsupervised time series anomaly detection.
Showing 6 of 60+. The full catalog (with quantisations, hardware variants, and per-region pricing) lives in the Yobibyte console.
Quick start
Five lines to your first data analytics call.
Every model in this category is reachable from the same Yobitel SDK. Swap the model name; the rest of the call shape stays identical. Authenticated via your workspace key.
from yobitel import Inference
import pandas as pd
# TimesFM — zero-shot time-series forecasting
client = Inference(model="google/timesfm")
df = pd.read_csv("sales.csv", parse_dates=["date"])
forecast = client.forecast(
series=df["revenue"],
horizon=30, # forecast 30 days ahead
interval=(0.05, 0.95), # 90% confidence band
)
forecast.plot()Where teams ship this
Real data analytics. In production.
Four use cases that customers run today. Pick a model from the lineup above, deploy on Yobibyte, plug it into the surrounding stack. Done.
- 01
Demand and revenue forecasting
- 02
Fraud and anomaly detection
- 03
Customer churn and propensity scoring
- 04
Capacity planning and SRE
Frameworks
Bring what your team already knows
Yobitel handles the serving layer (GPU scheduling, KV cache, autoscaling, request batching) so your team focuses on the model and the product.
Learn about YobibyteExplore the rest
Other categories in the marketplace
Computer Vision
Object detection, image classification, segmentation
NLP & Language
Text generation, translation, sentiment, summarization
Generative AI
Image gen, text gen, code gen, multimodal
Automation & RPA
Process automation, workflow AI, document processing
Industry-Specific
Vertical-specific models by industry
Speech & Audio
ASR, TTS, speaker diarization, audio classification
Recommendation
Recommender systems, personalization, content matching
Related Yobitel services
The teams behind Data Analytics
Marketplace listings are the model layer. When the work needs labelled data, evaluation harnesses, production serving, or end-to-end pipelines, these are the Yobitel services teams that build them.
Yobitel service
Domain-grounded annotation
Subject-matter expert labelling for tabular, financial, medical, and legal data.
Open serviceYobitel service
Eval sets
Statistical evaluation harnesses for forecasting and time-series workflows.
Open serviceYobitel service
AI pipelines
End-to-end data pipelines: ingest, transform, train, evaluate, ship.
Open serviceYobitel service
Infrastructure architecture
GPU + storage + network sizing for analytics workloads at scale.
Open serviceDon't see what you need?
Bring your own model or fine-tune one of ours. Yobitel engineers can sit with your team and ship the right stack.