WHAT’S NEW

New AI models.
Keep up without the noise.

The latest source listings from makers we track, covering language, images, video, audio, and 3D. Catalog checked Oct 30, 2026.

Sorted by the date a source repository was created, which may precede public release. This is a feed of new listings, not confirmed release announcements. Downloadable weights do not automatically mean an open-source license. Coverage and date meanings.

Other listings

937 dated records

BAAI · Downloadable

AltCLIP-m18

VisionImage classification

Hugging Face lists its task as zero-shot image classification. See the model card for supported inputs and setup.

Source listed
Mar 27, 2023
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

BAAI · Downloadable

Painter

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Mar 24, 2023
Parameters
Not reported
4-bit weights only
Not reported
License
mit
Compare this model →

Z.ai · Downloadable

chatglm-6b

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Mar 13, 2023
Parameters
6B
4-bit weights only
≈ 3 GB
License
Not disclosed
Compare this model →

Stability AI · Downloadable

sd-x2-latent-upscaler

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Feb 3, 2023
Parameters
372.6M
4-bit weights only
≈ 0.2 GB
License
openrail++
Compare this model →

Stability AI · Downloadable

stable-diffusion-x4-upscaler

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Nov 23, 2022
Parameters
473.4M
4-bit weights only
≈ 0.2 GB
License
openrail++
Compare this model →

BAAI · Downloadable

EVA

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Nov 21, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
mit
Compare this model →

BAAI · Downloadable

AltCLIP

VisionImage classification

Hugging Face lists its task as zero-shot image classification. See the model card for supported inputs and setup.

Source listed
Nov 15, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
creativeml-openrail-m
Compare this model →

pyannote · Downloadable

brouhaha

Capabilities unconfirmed

Hugging Face lists its task as voice activity detection. See the model card for supported inputs and setup.

Source listed
Oct 28, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
openrail
Compare this model →

Stability AI · Downloadable

sd-vae-ft-ema

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Oct 13, 2022
Parameters
83.7M
4-bit weights only
≈ 0 GB
License
mit
Compare this model →

Stability AI · Downloadable

sd-vae-ft-mse

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Oct 13, 2022
Parameters
83.7M
4-bit weights only
≈ 0 GB
License
mit
Compare this model →

OpenMOSS · Downloadable

elasticbert-chinese-base

Fill-mask

Hugging Face lists its task as fill-mask. See the model card for supported inputs and setup.

Source listed
Sep 14, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

Z.ai · Downloadable

CogVideo

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Jul 18, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

Z.ai · Downloadable

CogView2

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Jun 22, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
apache-2.0
Compare this model →

OpenAI · Downloadable

clip-vit-large-patch14-336

VisionImage classification

Hugging Face lists its task as zero-shot image classification. See the model card for supported inputs and setup.

Source listed
Apr 22, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

OpenAI · Downloadable

clip-vit-base-patch16

VisionImage classification

Hugging Face lists its task as zero-shot image classification. See the model card for supported inputs and setup.

Source listed
Mar 2, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

OpenAI · Downloadable

clip-vit-base-patch32

VisionImage classification

Hugging Face lists its task as zero-shot image classification. See the model card for supported inputs and setup.

Source listed
Mar 2, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

OpenAI · Downloadable

clip-vit-large-patch14

VisionImage classification

Hugging Face lists its task as zero-shot image classification. See the model card for supported inputs and setup.

Source listed
Mar 2, 2022
Parameters
427.6M
4-bit weights only
≈ 0.2 GB
License
Not disclosed
Compare this model →

OpenAI · Downloadable

imagegpt-large

Vision

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Mar 2, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
apache-2.0
Compare this model →

OpenAI · Downloadable

imagegpt-medium

Vision

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Mar 2, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
apache-2.0
Compare this model →

OpenAI · Downloadable

imagegpt-small

Vision

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Mar 2, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
apache-2.0
Compare this model →

OpenMOSS · Downloadable

cpt-large

Text classificationSummarizationFill-mask

Hugging Face lists its task as text classification. See the model card for supported inputs and setup.

Source listed
Mar 2, 2022
Parameters
424.2M
4-bit weights only
≈ 0.2 GB
License
Not disclosed
Compare this model →

OpenMOSS · Downloadable

elasticbert-base

Fill-mask

Hugging Face lists its task as fill-mask. See the model card for supported inputs and setup.

Source listed
Mar 2, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

OpenMOSS · Downloadable

elasticbert-large

Fill-mask

Hugging Face lists its task as fill-mask. See the model card for supported inputs and setup.

Source listed
Mar 2, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

pyannote · Downloadable

embedding

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Source listed
Mar 2, 2022
Parameters
Not reported
4-bit weights only
Not reported
License
mit
Compare this model →

What makes this feed useful?

Capability tags distinguish a model that reads images from one that creates them. Each listing links to its source and a permanent profile, so you can inspect its license and compare it with a model you already know.

Does this cover every new release?

No. The current feed tracks public Hugging Face metadata from selected makers. It can miss untracked makers, cloud-only releases, and records beyond a source’s retrieval limit. Announced models without a source listing are not included. Check Sources & methodology for the current coverage.

Listings update with the catalog automatically. A missing or delayed source can leave older information visible; each model profile shows when it was checked.