TabFM

TabFM

Google
+
+

Related Products

  • NeuBird
    2 Ratings
    Visit Website
  • Checksum.ai
    1 Rating
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Dialpad Support
    1,600 Ratings
    Visit Website
  • RetailEdge
    201 Ratings
    Visit Website
  • Uptime.com
    478 Ratings
    Visit Website
  • Zendesk
    7,958 Ratings
    Visit Website
  • Nexo
    18,609 Ratings
    Visit Website
  • Planview AdaptiveWork
    714 Ratings
    Visit Website
  • Forethought
    166 Ratings
    Visit Website

About

Step 3.5 Flash is an advanced open source foundation language model engineered for frontier reasoning and agentic capabilities with exceptional efficiency, built on a sparse Mixture of Experts (MoE) architecture that selectively activates only about 11 billion of its ~196 billion parameters per token to deliver high-density intelligence and real-time responsiveness. Its 3-way Multi-Token Prediction (MTP-3) enables generation throughput in the hundreds of tokens per second for complex multi-step reasoning chains and task execution, and it supports efficient long contexts with a hybrid sliding window attention approach that reduces computational overhead across large datasets or codebases. It demonstrates robust performance on benchmarks for reasoning, coding, and agentic tasks, rivaling or exceeding many larger proprietary models, and includes a scalable reinforcement learning framework for consistent self-improvement.

About

TabFM is a zero-shot foundation model for tabular data, designed to simplify classification and regression workflows that traditionally require manual model training, hyperparameter tuning, and domain-specific feature engineering. Built specifically for tables, TabFM reframes tabular prediction as an in-context learning problem: instead of fitting a new supervised model to each dataset, it takes historical training examples and target testing rows together as one unified prompt, then interprets relationships between columns and rows at inference time. Because tables are two-dimensional and orderless, TabFM uses a hybrid architecture that combines alternating row and column attention, row compression, and a dedicated Transformer for in-context learning over compressed row embeddings. This design lets the model capture complex feature interactions and dependencies while keeping prediction computationally efficient for larger datasets.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Developers, researchers, and AI engineers who want a powerful open source foundational AI model capable of fast, deep reasoning, coding assistance, and agentic task execution

Audience

Data scientists and analytics teams that need accurate tabular classification and regression without repetitive training, tuning, and feature-engineering work

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version
Free Trial

Pricing

Free
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

StepFun
Founded: 2023
China
static.stepfun.com/blog/step-3.5-flash/

Company Information

Google
Founded: 1998
United States
research.google/blog/introducing-tabfm-a-zero-shot-foundation-model-for-tabular-data/

Alternatives

MiMo-V2-Flash

MiMo-V2-Flash

Xiaomi Technology

Alternatives

Evo 2

Evo 2

Arc Institute
LongCat-2.0

LongCat-2.0

LongCat
MLBox

MLBox

Axel ARONIO DE ROMBLAY

Categories

Categories

Integrations

GitHub
Hugging Face
ModelScope
arXiv

Integrations

GitHub
Hugging Face
ModelScope
arXiv
Claim Step 3.5 Flash and update features and information
Claim Step 3.5 Flash and update features and information
Claim TabFM and update features and information
Claim TabFM and update features and information