Parameter-efficient tabular FMs
Why train a 70M-parameter model when a 13M-parameter one matches it within 4 pp? We focus on the small end of the size/accuracy frontier where models run on a laptop and can be audited end-to-end.
Independent AI research lab · Bratislava · v1 launched 2026-05-27
A 13M-parameter tabular foundation model. Open weights. Calibrated outputs. Apache-2.0.
0.751 classification accuracy / 0.609 regression R² on a locked 25-dataset OpenML benchmark. Apache-2.0. Calibrated outputs — returns full prediction confidence intervals, not just point estimates.
- Status
- v1 launched · May 2026
- Models
- 2 open-weight
- License
- Apache-2.0
- HQ
- Bratislava · EU
What we research
Where we focus
The next decade of AI will be defined as much by what models can do with tables of data as by what they can do with text. Most real business decisions still happen on rows and columns. We're closing the gap, openly.
Calibrated uncertainty
A prediction without a confidence interval is a guess. Our regression head returns full predictive distributions over 1024 quantile bins, not point estimates. Calibration is a first-class objective, not an afterthought.
Agent-native ML tooling
LLMs aren't built for numerical inference. Our models ship as MCP tools that any LLM agent can call. The agent reasons; the model predicts. We treat the LLM–tool boundary as a first-class research problem.
Open weights
Two checkpoints. One interface.
PredictLM‑Mini
13M parameters · 54 MB · Apache-2.0
The smallest open-weight tabular foundation model with calibrated uncertainty. Statistically tied with Base on classification and within ~4 percentage points R² on regression. Runs on any modern laptop.
- Runs on any modern laptop — no GPU required
- ~95% of Base's accuracy at half the size
- ~2-3 seconds per prediction on a MacBook
- Returns class probabilities and full regression confidence intervals
PredictLM‑Base
26M parameters · 105 MB · Apache-2.0
The best-accuracy model in the family. Teacher for Mini and the architecture of record for our published evaluations. Apache-2.0 across the board — suitable for commercial deployment.
- Highest-accuracy model in the family
- Out of the box: 0.685 classification accuracy / 0.589 regression R² on 25 OpenML datasets
- Combined with Mini + test-time training: 0.751 / 0.609
- Competitive with XGBoost on regression
Get started
Try it in Python.
One pip install. One PredictLM object. Returns class probabilities and full regression confidence intervals.
pythonpredictlm.py
from predictlm import PredictLM
import pandas as pd
# One model object — partner ckpt is auto-downloaded on first .predict()
# and the package runs the published Duo + TTT recipe under the hood.
model = PredictLM.from_pretrained(
"zerooneresearch/predictlm-mini-13m"
)
X_train = pd.DataFrame(...) # labeled context rows
y_train = pd.Series(...) # labels (float = regression, int/str = cls)
X_test = pd.DataFrame(...) # rows you want predictions for
# 0.751 cls / 0.609 reg on the locked OpenML benchmark.
preds = model.fit(X_train, y_train).predict(X_test)
probs = model.predict_proba(X_test)Also available as an MCP server for Claude Desktop, Cursor, and Continue. See setup →
How it works
Three steps. No training required.
PredictLM is pre-trained. You don't fine-tune it. You give it your data, and it predicts.
01
Give it your data
A CSV or DataFrame with rows you have labels for, plus rows you want predictions for. Up to 128 features per row. Classification or regression — the model figures out which.
02
PredictLM learns the pattern
In ~2-15 seconds (depending on dataset size), the model adapts to your specific task using its pre-trained representations. No GPU required for Mini. No hyperparameter tuning.
03
Get calibrated predictions
Not just point predictions — full probability distributions. For regression you get a 1024-bin posterior. For classification, calibrated class probabilities. Everything you need for downstream decisions.
Try it in your browser — no install needed.
Launch the live demoUse cases
Where tabular foundation models actually ship.
The biggest business decisions still run on tables. PredictLM gives those tables the same lift LLMs gave text.
Financial Services
- Fraud transaction scoring
- Credit default prediction
- Churn probability
Healthcare
- Patient outcome prediction
- Lab result classification
- Treatment response modeling
Manufacturing
- Predictive maintenance
- Anomaly detection in sensors
- Quality control
Retail & Marketing
- Customer LTV scoring
- Conversion prediction
- Demand forecasting
Apache-2.0 license, open weights — deployable on your own infrastructure for regulated industries.
Latest
Recent research.
Model release · 2026-05-27
PredictLM-Mini: a 13M tabular foundation model with calibrated uncertainty
The smallest checkpoint in the family. Distilled from a 26M Base. Runs on a laptop. The launch release.
ReadTechnical · 2026-05-27
Six architectural experiments. Five lost. Here's what we shipped.
Before settling on Mini's architecture, we ran six experiments at the 26M-57M scale. Five lost to the smaller model. Here's the full writeup.
ReadTechnical · 2026-05-27
BarDistribution: why every regressor should return a distribution.
A 1024-bin output for regression is the difference between a guess and a calibrated prediction. Why we use it and how to use it.
Read