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 Nov 2, 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.

Latest listings

3,185 dated records

Stability AI · Downloadable

stable-virtual-camera

Video generation

Generates video. Resolution, clip length, and speed depend on the version and setup.

Source listed
Feb 19, 2025
Parameters
1.3B
4-bit weights only
≈ 0.6 GB
License
other
Compare this model →

Microsoft · Downloadable

bioemu

Capabilities unconfirmed

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

Source listed
Feb 19, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
mit
Compare this model →

Google · Downloadable

siglip2-so400m-patch16-naflex

VisionImage classification

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

Source listed
Feb 18, 2025
Parameters
1.1B
4-bit weights only
≈ 0.6 GB
License
apache-2.0
Compare this model →

Google · Downloadable

siglip2-base-patch16-naflex

VisionImage classification

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

Source listed
Feb 18, 2025
Parameters
375.2M
4-bit weights only
≈ 0.2 GB
License
apache-2.0
Compare this model →

Google · Downloadable

siglip2-so400m-patch16-512

VisionImage classification

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

Source listed
Feb 17, 2025
Parameters
1.1B
4-bit weights only
≈ 0.6 GB
License
apache-2.0
Compare this model →

Google · Downloadable

siglip2-so400m-patch16-384

VisionImage classification

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

Source listed
Feb 17, 2025
Parameters
1.1B
4-bit weights only
≈ 0.6 GB
License
apache-2.0
Compare this model →

Google · Downloadable

siglip2-so400m-patch16-256

VisionImage classification

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

Source listed
Feb 17, 2025
Parameters
1.1B
4-bit weights only
≈ 0.6 GB
License
apache-2.0
Compare this model →

Google · Downloadable

siglip2-so400m-patch14-384

VisionImage classification

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

Source listed
Feb 17, 2025
Parameters
1.1B
4-bit weights only
≈ 0.6 GB
License
apache-2.0
Compare this model →

Google · Downloadable

siglip2-so400m-patch14-224

VisionImage classification

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

Source listed
Feb 17, 2025
Parameters
1.1B
4-bit weights only
≈ 0.6 GB
License
apache-2.0
Compare this model →

Google · Downloadable

siglip2-giant-opt-patch16-384

VisionImage classification

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

Source listed
Feb 17, 2025
Parameters
1.9B
4-bit weights only
≈ 0.9 GB
License
apache-2.0
Compare this model →

StepFun · Downloadable

stepvideo-t2v

Video generation

Generates video. Resolution, clip length, and speed depend on the version and setup.

Source listed
Feb 14, 2025
Parameters
29.3B
4-bit weights only
≈ 14.7 GB
License
mit
Compare this model →

StepFun · Downloadable

Step-Audio-TTS-3B

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Feb 13, 2025
Parameters
3B
4-bit weights only
≈ 1.5 GB
License
apache-2.0
Compare this model →

StepFun · Downloadable

Step-Audio-Tokenizer

Capabilities unconfirmed

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

Source listed
Feb 13, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
apache-2.0
Compare this model →

StepFun · Downloadable

Step-Audio-Chat

Capabilities unconfirmed

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Feb 13, 2025
Parameters
131.9B
4-bit weights only
≈ 66 GB
License
apache-2.0
Compare this model →

StepFun · Downloadable

stepvideo-t2v-turbo

Capabilities unconfirmed

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

Source listed
Feb 12, 2025
Parameters
29.3B
4-bit weights only
≈ 14.7 GB
License
mit
Compare this model →

Microsoft · Downloadable

OmniParser-v2.0

Capabilities unconfirmed

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

Source listed
Feb 12, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
mit
Compare this model →

Microsoft · Downloadable

wham

Capabilities unconfirmed

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

Source listed
Feb 11, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

Kyutai · Downloadable

hibiki-2b-rs

Translation

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

Source listed
Feb 9, 2025
Parameters
2B
4-bit weights only
≈ 1 GB
License
cc-by-4.0
Compare this model →

BAAI · Downloadable

EVE-7B-HD-v2.0

Text generation

Generates text, according to its published model architecture (EVEQwen2ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Source listed
Feb 8, 2025
Parameters
7B
4-bit weights only
≈ 3.5 GB
License
apache-2.0
Compare this model →

Kyutai · Downloadable

hibiki-1b-rs

Translation

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

Source listed
Feb 6, 2025
Parameters
1B
4-bit weights only
≈ 0.5 GB
License
cc-by-4.0
Compare this model →

Kyutai · Downloadable

hibiki-1b-pytorch

Translation

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

Source listed
Feb 6, 2025
Parameters
1B
4-bit weights only
≈ 0.5 GB
License
cc-by-4.0
Compare this model →

Kyutai · Downloadable

hibiki-2b-pytorch

Translation

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

Source listed
Feb 6, 2025
Parameters
2B
4-bit weights only
≈ 1 GB
License
cc-by-4.0
Compare this model →

Kyutai · Downloadable

hibiki-2b-mlx

Translation

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

Source listed
Feb 5, 2025
Parameters
2B
4-bit weights only
≈ 1 GB
License
cc-by-4.0
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.