TabPFN Scaling Mode
Tabular Foundation Model on millions of rows
Details
- External ID
- 46138439
- Source
- HN
- Company
- —
- Product
- TabPFN Scaling Mode
- Website domain
- priorlabs.ai
- Launched
- Dec. 3, 2025
- Cohort
- —
- Upvotes
- 5
- Upvotes percentile
- 0.10400763358778627
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
I’m excited to announce Scaling Mode for TabPFN-2.5, our tabular foundation model (Large Tabular Model). This removes any fixed upper limits on dataset sizes and extends TabPFN to datasets with millions of rows.What is Scaling Mode? A new pipeline around TabPFN-2.5 designed for large-N workloads, which removes the fixed row limit of TabPFN. The system works with large training sets, constrained only by your compute and memory.We benchmarked Scaling Mode on datasets ranging from 1M to 10M rows, comparing against CatBoost, XGBoost, and LightGBM. Key findings:- Scaling Mode enables TabPFN-2.5 to continue improving performance with more data- Scales dramatically better than TabPFN-2.5 with 50K subsampling- No evidence of the performance gap to gradient boosting shrinking as we scale up- Performance continues to improve strongly with more data on the largest tested datasetsTo quickly summarise our progress, here's the history of our scaling trajectory:- TabPFN v2 (Jan 2025): 10K rows- TabPFN-2.5 (Nov 2025): 50K rows- Scaling Mode (today): 10M+ rows testedCurrent limitations: Scaling Mode is designed for companies for now. If you’re working with data at a large scale and want to test it, access is currently only by request to ensure we can support early users properly.Full blog post: https://priorlabs.ai/technical-reports/large-data-modelRequest access: https://priorlabs.ai/tabpfn/large-dataWould love to hear feedback from anyone working with large tabular datasets!
Enrichment
- Theme
- lightweight and on-device AI runtimes
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- tabular foundation model for large datasets
- Manually corrected
- False
Could you build this?
No TabPFN is an academic breakthrough foundation model for tabular data trained using Prior-Data Fitted Networks on massive GPU clusters.
What it would actually take: Requires proprietary research in synthetic dataset generation, Bayesian neural networks, and transformer architectures adapted for tabular in-context learning. Scaling to millions of rows involves custom approximate inference, chunked cross-attention kernels, and massive distributed training infrastructure across specialized accelerators.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one — 22 launches clear the similarity bar, closest 8 shown.
Attention rank: #19 of 23 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 35 days after the earliest competitor.
- TabPFN-2.5 · hn · 2025-11-06 · 73 upvotes · similarity 0.71
- TabPFN MCP, gives LLMs tools for predictions on tabular data (beta) · hn · 2026-02-05 · 11 upvotes · similarity 0.51
- TabPFN-3.5, a Tabular Foundation Model for messy real-world tables · hn · 2026-09-15 · 10 upvotes · similarity 0.43
- causilo · github · 2026-09-13 · 64 upvotes · similarity 0.40
- Python SDK · hn · 2025-12-18 · 43 upvotes · similarity 0.40
- excel-large-dataset-optimization-tools · github · 2026-09-10 · 10 upvotes · similarity 0.39
- Datalevin · hn · 2026-07-21 · 8 upvotes · similarity 0.36
- Optimize Databricks SQL · hn · 2025-10-29 · 6 upvotes · similarity 0.35
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.