Skip to page content
SAVRN
Search Plan a project

SAVRN Model Hub

Open-Weight Models

An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.

Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.

11,122Models
3,164Datasets
285Papers
6,792Publishers
11,852Sourced relationships

Updated 2026-10-18 · How the library is built

Most downloadedMost likedRecently updatedNameLargest

11,122 models, sorted by most downloaded.

Models SpawnScene (https://spawnscene.com) runs on SpawnDev.ILGPU.ML in the browser, in a form that engine takes. MI-GAN (Picsart AI Research, "MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices", ICCV 2023), the plain 512 network migan.onnx from https://huggingface.co/andraniksargsyan/migan, MIT licence (LICENSE-MI-GAN, unchanged). Changed: float32 I/O instead of uint8 - inputs image [B,3,H,W] and mask [B,1,H,W] are FLOAT (values 0..255; mask 255 = known pixel, 0 = fill), the output result [B,3,H,W] is FLOAT 0..255, and the graph's four Cast(to=uint8) became Cast(to=float). Weights untouched. Against the original on onnxruntime: max |difference| 1/255 (rounding).

Open weights mit
View model

Model · Image classification

species-classifier-arachnids

Michael G

A 153-species arachnid classifier (spiders, scorpions, ticks, harvestmen) small enough for microcontrollers and the Coral Edge TPU. MobileNetV2 at full width and 160 px, full-integer int8, trained on the iNaturalist 2021 competition data. It fills the gap people hit first with Google's AIY insect model, which has no spiders. Part of species-classifiers. Measured on the int8 file over the 1,530 iNaturalist 2021 validation images for these species (10 per species), with an 87.5% centre crop: The PyTorch checkpoint scores 64.4% top-1. For comparison, Google's stock AIY insect model scores 59.1% top-1 on the iNat2021 species it shares, choosing among 1,022 classes. - Input [1, 160, 160, 3]…

Open weights apache-2.0 tflite
View model

Model · Image classification

species-classifier-mammals

Michael G

A 246-species mammal classifier small enough for microcontrollers and the Coral Edge TPU. MobileNetV2 at full width and 160 px, full-integer int8, trained on the iNaturalist 2021 competition data. Part of species-classifiers, which also rescues Google's AIY Vision Kit insect, plant and bird models into the same shape. Measured on the int8 file over the 2,460 iNaturalist 2021 validation images for these species (10 per species), with an 87.5% centre crop: The PyTorch checkpoint scores 56.1% top-1; int8 costs about a point. Grayscale is reported because the model was trained with 20% random grayscale so it holds up on monochrome cameras such as the Coral Dev Board Micro's. For comparison…

Open weights apache-2.0 tflite
View model

Model

spi

Holder

Evidence-backed orchestration for generative media production. Not a text-to-video wrapper: SPI plans a production as structured state, renders it through swappable model backends, verifies results with evidence-carrying metrics, and (planned) repairs only what failed. See docs/architecture.md for the component map and docs/researchreport.md for the Phase-2 backend decision (Wan 2.2, Apache-2.0; LTX-2 as fast secondary). Mock mode (SPIMODE=mock equivalent: SPIApi(mode="mock")) needs no GPU. - SPIMODE=mock — zero GPU, deterministic artifacts (current default) - SPIMODE=small — reserved for Wan 2.1-1.3B / LTX-Video-2B smoke tests (Phase 2) - SPIMODE=production — reserved for Wan 2.2 A14B…

Open weights
View model

Model Collections

Hand-picked starting points, each with the reason it exists.

Collection · 4 entries

Models that fit on one accelerator

Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.

View collection

Open-Weight Models Explained

What is an open-weight model?

An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.

Is an open-weight model the same as open source?

Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.

Can I use an open-weight model commercially?

It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.

How much memory does an open-weight model need?

About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.

Related SAVRN Research

The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.