# mitra-classifier by Autogluon: Open-Weight Model Source: https://savrn.com/models/mitra-classifier Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve mitra-classifier (76M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [mitra-classifier on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/mitra-classifier/gpus) ## SAVRN's Notes on mitra-classifier Mitra brings the foundation-model idea to spreadsheets. It is a tabular classifier pretrained entirely on synthetic data, and it learns a new table in context, without gradient training, at prediction time. At 76M parameters it is light. Apache 2.0 allows commercial use. For small and medium tabular problems it is worth a test, because it needs almost no setup. Benchmark it against gradient boosting on your own data before you switch; on large tables, the classic methods are hard to beat. SAVRN Research, 2026-09-18 ## Model Card By Autogluon, published under apache-2.0, revision c425e9fa0910. Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers. ### Architecture Mitra is based on a 12-layer Transformer of 72 M parameters, pre-trained by incorporating an in-context learning paradigm. ### Usage To use Mitra classifier, install AutoGluon by running: ``` pip install uv uv pip install autogluon.tabular[mitra] ``` A minimal example showing how to perform inference using the Mitra classifier: [Read the full model card (296 words)](https://savrn.com/models/mitra-classifier/card) ## Identity and Version Repository autogluon/mitra-classifier Publisher Autogluon Task Tabular classification Modality Tabular Library Not stated by the source Parameters 76M parameters Languages Not stated by the source Revision c425e9fa0910a6be1c494321792e7ba2a1367b1a First published 2025-06-22 Last updated 2025-11-19 ## Files and Weights 4 files, 302.7 MB in total. The weights are 1 file totalling 302.7 MB in safetensors. Weights1 file · 302.7 MB Configuration1 file · 86 B Documentation1 file · 3.4 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 302.7 MB | e06a055e91a3 | | config.json | Configuration | 86 B | — | | README.md | Documentation | 3.4 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 302.7 MB [Download from Autogluon](https://huggingface.co/autogluon/mitra-classifier) Released by Autogluon through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:2510.21204](https://savrn.com/papers/mitra-mixed-synthetic-priors-for-enhancing-tabular-foundation-models) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 302.7 MB | | 16-bit | 0.2 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About mitra-classifier ### How much GPU memory does mitra-classifier need? About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (76M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run mitra-classifier on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use mitra-classifier commercially? Yes. mitra-classifier is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ## Similar Models Model · Tabular classification ### [mitra-classifier-2](https://savrn.com/models/mitra-classifier-2) [Autogluon](https://savrn.com/model-publishers/autogluon) Mitra-v2 classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers, including the new Hybrid SCM prior. It is the second generation of the Mitra classifier (autogluon/mitra-classifier), pre-trained with a 10x longer context, three times as many features, and an improved optimizer. On the TabArena and TALENT benchmarks it delivers state-of-the-art accuracy at the level of TabFM and EXAONE Tabular, while surpassing TabPFN-3 by a wide margin. The regression model is at autogluon/mitra-regressor-2, and the inference and fine-tuning code with our evaluation results is at autogluon/mitra-finetune. Mitra-v2 is based on a… Open weights apache-2.0 76M parameters [View model](https://savrn.com/models/mitra-classifier-2) Model · Tabular classification ### [mitra-classifier-1.1](https://savrn.com/models/mitra-classifier-1-1) [Autogluon](https://savrn.com/model-publishers/autogluon) Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers. Mitra is based on a 12-layer Transformer of 72 M parameters, pre-trained by incorporating an in-context learning paradigm. To use Mitra classifier, install AutoGluon by running: A minimal example showing how to perform inference using the Mitra classifier: A minimal example showing how to perform fine-tuning using the Mitra classifier: This project is licensed under the Apache-2.0 License. Amazon Science blog: Mitra: Mixed synthetic priors for enhancing tabular foundation models Open weights apache-2.0 76M parameters [View model](https://savrn.com/models/mitra-classifier-1-1) Model · Tabular classification ### [rt-j](https://savrn.com/models/rt-j) [Stanford Tabular and Relational (STAR) Project](https://savrn.com/model-publishers/stanford-star) Open weights cc-by-nc-sa-4.0 86M parameters [View model](https://savrn.com/models/rt-j) Model · Tabular classification ### [rt-plurel](https://savrn.com/models/rt-plurel) [Stanford Tabular and Relational (STAR) Project](https://savrn.com/model-publishers/stanford-star) RT-PluRel is a Relational Transformer checkpoint pair for in-context / few-shot entity prediction over multi-table relational databases (no per-task gradient training). Same architecture and file layout as stanford-star/rt-j — drop-in replacement. Architecture: ~85.6M blocks, dmodel 512, 8 heads, dff 2048 · text columns embedded with all-MiniLM-L12-v2 (dtext 384). Each folder contains model.safetensors (weights) and config.json (dims + text-embedding model). The paper/ subdirectory preserves the earlier RT-PluRel release:.pt checkpoints (12 blocks, dmodel 256, dff 1024) pretrained on synthetic relational databases generated by PluRel, plus the continued-pretraining and fine-tuned RelBench… Open weights cc-by-nc-sa-4.0 86M parameters pytorch [View model](https://savrn.com/models/rt-plurel) Model · Tabular classification ### [DigitalEduTransformers](https://savrn.com/models/digitaledutransformers) [SnowFlash383935](https://savrn.com/model-publishers/snowflash383935) Модель для соревнования DigitalEdu с использованием трансформеров. 9 эпох. Пример вывода: [False, True] Open weights gpl-3.0 101M parameters transformers [View model](https://savrn.com/models/digitaledutransformers) Model · Tabular classification ### [TabSTAR](https://savrn.com/models/tabstar) [Alan Arazi](https://savrn.com/model-publishers/alana89) To fit a pretrained TabSTAR model to your own dataset, install the package: Paper: TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations Open weights cc-by-4.0 47M parameters [View model](https://savrn.com/models/tabstar) ## Autogluon [All models and datasets](https://savrn.com/model-publishers/autogluon) ## Versions - [c425e9fa0910](https://savrn.com/models/mitra-classifier/versions/c425e9fa0910) · current 2026-09-18 ## Explore More - [All tabular classification models](https://savrn.com/models/tasks/tabular-classification) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Autogluon website](https://auto.gluon.ai/) - [Hugging Face record](https://huggingface.co/autogluon/mitra-classifier) - [How the hub is built](https://savrn.com/model-hub/methodology)