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

Wan · Alibaba · Downloadable

Wan2.1-T2V-1.3B

Video generation

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

Source listed: Feb 25, 2025
Parameters: 1.3B
4-bit weights only: ≈ 0.7 GB
License: apache-2.0

Compare this model →

Wan · Alibaba · Downloadable

Wan2.1-I2V-14B-720P

Video generation

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

Source listed: Feb 25, 2025
Parameters: 14B
4-bit weights only: ≈ 7 GB
License: apache-2.0

Compare this model →

Wan · Alibaba · Downloadable

Wan2.1-I2V-14B-480P

Video generation

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

Source listed: Feb 25, 2025
Parameters: 14B
4-bit weights only: ≈ 7 GB
License: apache-2.0

Compare this model →

Wan · Alibaba · Downloadable

Wan2.1-T2V-14B

Video generation

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

Source listed: Feb 25, 2025
Parameters: 14B
4-bit weights only: ≈ 7 GB
License: apache-2.0

Compare this model →

BAAI · Downloadable

BGE-VL-large

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Source listed: Feb 25, 2025
Parameters: 427.6M
4-bit weights only: ≈ 0.2 GB
License: mit

Compare this model →

BAAI · Downloadable

BGE-VL-base

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Source listed: Feb 25, 2025
Parameters: 149.6M
4-bit weights only: ≈ 0.1 GB
License: mit

Compare this model →

Microsoft · Downloadable

Phi-4-multimodal-instruct

VisionTranscriptionAudio understanding

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

Source listed: Feb 24, 2025
Parameters: 5.6B
4-bit weights only: ≈ 2.8 GB
License: mit

Compare this model →

Microsoft · Downloadable

Magma-8B

Robotics

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

Source listed: Feb 23, 2025
Parameters: 8B
4-bit weights only: ≈ 4 GB
License: mit

Compare this model →

Moonshot AI · Downloadable

Moonlight-16B-A3B-Instruct

Text generation

Generates text for conversations and writing.

Source listed: Feb 22, 2025
Parameters: 16B
4-bit weights only: ≈ 8 GB
License: mit

Compare this model →

Moonshot AI · Downloadable

Moonlight-16B-A3B

Text generation

Generates text for conversations and writing.

Source listed: Feb 22, 2025
Parameters: 16B
4-bit weights only: ≈ 8 GB
License: mit

Compare this model →

Google · Downloadable

gemma-3-1b-pt

Text generation

Generates text for conversations and writing.

Source listed: Feb 20, 2025
Parameters: 1B
4-bit weights only: ≈ 0.5 GB
License: gemma

Compare this model →

Google · Downloadable

gemma-3-4b-it

Vision

Understands text and images and responds in text.

Source listed: Feb 20, 2025
Parameters: 4B
4-bit weights only: ≈ 2 GB
License: gemma

Compare this model →

Google · Downloadable

gemma-3-4b-pt

Vision

Understands text and images and responds in text.

Source listed: Feb 20, 2025
Parameters: 4B
4-bit weights only: ≈ 2 GB
License: gemma

Compare this model →

Google · Downloadable

siglip2-large-patch16-512-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Google · Downloadable

siglip2-large-patch16-384-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Google · Downloadable

siglip2-large-patch16-256-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Google · Downloadable

siglip2-giant-opt-patch16-256-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Google · Downloadable

siglip2-base-patch32-256-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Google · Downloadable

siglip2-base-patch16-512-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Google · Downloadable

siglip2-base-patch16-384-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Stability AI · Downloadable

sv4d2.0

Capabilities unconfirmed

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: other

Compare this model →

Google · Downloadable

siglip2-base-patch16-256-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Google · Downloadable

siglip2-base-patch16-224-jax

VisionImage classification

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

OpenMOSS · Downloadable

Llama-Scope-R1-Distill

Capabilities unconfirmed

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

Source listed: Feb 20, 2025
Parameters: Not reported
4-bit weights only: Not reported
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.