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 29, 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

OpenMOSS · Downloadable

RoboOmni

VisionRobotics

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

Source listed
Oct 28, 2025
Parameters
4.7B
4-bit weights only
≈ 2.4 GB
License
cc-by-nc-4.0
Compare this model →

inclusionAI · Downloadable

LLaDA-MoE-7B-A1B-Instruct-TD

Capabilities unconfirmed

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

Source listed
Oct 28, 2025
Parameters
7B
4-bit weights only
≈ 3.5 GB
License
apache-2.0
Compare this model →

BRIA AI · Downloadable

FIBO-VLM-prompt-to-JSON

Capabilities unconfirmed

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

Source listed
Oct 27, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
cc-by-nc-4.0
Compare this model →

BRIA AI · Downloadable

FIBO-gemini-prompt-to-JSON

Capabilities unconfirmed

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

Source listed
Oct 27, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
cc-by-nc-4.0
Compare this model →

Z.ai · Downloadable

Kaleido-14B-S2V

Capabilities unconfirmed

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

Source listed
Oct 27, 2025
Parameters
14B
4-bit weights only
≈ 7 GB
License
mit
Compare this model →

LightOn · Downloadable

LightOnOCR-0.9B-32k-1025

Document reading

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

Source listed
Oct 23, 2025
Parameters
900M
4-bit weights only
≈ 0.5 GB
License
apache-2.0
Compare this model →

LightOn · Downloadable

LightOnOCR-0.9B-16k-1025

Document reading

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

Source listed
Oct 23, 2025
Parameters
900M
4-bit weights only
≈ 0.5 GB
License
apache-2.0
Compare this model →

inclusionAI · Downloadable

Ming-VideoMAR

Capabilities unconfirmed

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

Source listed
Oct 22, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

inclusionAI · Preview

Ming-flash-omni-Preview

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Source listed
Oct 14, 2025
Parameters
104.4B
4-bit weights only
≈ 52.2 GB
License
mit
Compare this model →

Meta · Downloadable

pe-a-frame-large

Capabilities unconfirmed

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

Source listed
Oct 13, 2025
Parameters
1.5B
4-bit weights only
≈ 0.7 GB
License
apache-2.0
Compare this model →

Meta · Downloadable

pe-a-frame-base

Capabilities unconfirmed

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

Source listed
Oct 13, 2025
Parameters
560.6M
4-bit weights only
≈ 0.3 GB
License
apache-2.0
Compare this model →

Meta · Downloadable

pe-a-frame-small

Capabilities unconfirmed

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

Source listed
Oct 13, 2025
Parameters
439.7M
4-bit weights only
≈ 0.2 GB
License
apache-2.0
Compare this model →

inclusionAI · Downloadable

V2P-7B

Vision

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

Source listed
Oct 10, 2025
Parameters
7B
4-bit weights only
≈ 3.5 GB
License
apache-2.0
Compare this model →

OpenBMB · Downloadable

EVisRAG-3B

Capabilities unconfirmed

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

Source listed
Oct 7, 2025
Parameters
3B
4-bit weights only
≈ 1.5 GB
License
apache-2.0
Compare this model →

Meta · Downloadable

sam-3d-objects

3D generation

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

Source listed
Oct 6, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

Meta · Downloadable

SSDD

Capabilities unconfirmed

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

Source listed
Oct 6, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
cc-by-nc-4.0
Compare this model →

Meta · Downloadable

dacvae-watermarked

Capabilities unconfirmed

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

Source listed
Oct 3, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
apache-2.0
Compare this model →

Meta · Downloadable

pe-av-small-16-frame

Capabilities unconfirmed

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

Source listed
Oct 2, 2025
Parameters
847M
4-bit weights only
≈ 0.4 GB
License
apache-2.0
Compare this model →

Meta · Downloadable

pe-av-small

Capabilities unconfirmed

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

Source listed
Oct 2, 2025
Parameters
847M
4-bit weights only
≈ 0.4 GB
License
apache-2.0
Compare this model →

OpenBMB · Downloadable

EVisRAG-7B

Capabilities unconfirmed

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

Source listed
Oct 2, 2025
Parameters
7B
4-bit weights only
≈ 3.5 GB
License
apache-2.0
Compare this model →

inclusionAI · Downloadable

Ming-UniVision-16B-A3B

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Source listed
Sep 30, 2025
Parameters
16B
4-bit weights only
≈ 8 GB
License
apache-2.0
Compare this model →

Meta · Downloadable

pe-av-base

Capabilities unconfirmed

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

Source listed
Sep 30, 2025
Parameters
1B
4-bit weights only
≈ 0.5 GB
License
apache-2.0
Compare this model →

Meta · Downloadable

pe-av-base-16-frame

Capabilities unconfirmed

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

Source listed
Sep 30, 2025
Parameters
1B
4-bit weights only
≈ 0.5 GB
License
apache-2.0
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.