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.

Latest listings

3,183 dated records

Liquid AI · Downloadable

LFM2.5-Audio-1.5B

Audio generation

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

Source listed
Dec 18, 2025
Parameters
1.5B
4-bit weights only
≈ 0.8 GB
License
other
Compare this model →

Microsoft · Downloadable

simpoly

Capabilities unconfirmed

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

Source listed
Dec 18, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
mit
Compare this model →

Meta · Downloadable

map-anything-apache-v1

Vision3D generationDepth estimation

Creates 3D assets. Check the model card for supported inputs and output formats.

Source listed
Dec 18, 2025
Parameters
563.3M
4-bit weights only
≈ 0.3 GB
License
apache-2.0
Compare this model →

Meta · Downloadable

map-anything-v1

Vision3D generationDepth estimation

Creates 3D assets. Check the model card for supported inputs and output formats.

Source listed
Dec 18, 2025
Parameters
563.3M
4-bit weights only
≈ 0.3 GB
License
cc-by-nc-4.0
Compare this model →

Qwen · Alibaba · Downloadable

Qwen-Image-Layered

Capabilities unconfirmed

Creates or edits images. Check the model card for supported inputs and output settings.

Source listed
Dec 17, 2025
Parameters
20.4B
4-bit weights only
≈ 10.2 GB
License
apache-2.0
Compare this model →

Qwen · Alibaba · Downloadable

Qwen-Image-Edit-2511

Image generationImage editing

Creates or edits images. Check the model card for supported inputs and output settings.

Source listed
Dec 17, 2025
Parameters
20.4B
4-bit weights only
≈ 10.2 GB
License
apache-2.0
Compare this model →

Google · Preview

Gemini 3 Flash Preview

VisionVideo understandingAudio understandingReasoningTool use

Cloud API for vision, video understanding, audio understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Source listed
Dec 17, 2025
License
Provider terms
Compare this model →

Moondream · Downloadable

md3p-int4

Vision

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

Source listed
Dec 16, 2025
Parameters
2.5B
4-bit weights only
≈ 1.2 GB
License
apache-2.0
Compare this model →

Meta · Downloadable

pixio-vith16

Capabilities unconfirmed

Turns content into numerical representations for semantic search and retrieval.

Source listed
Dec 16, 2025
Parameters
631M
4-bit weights only
≈ 0.3 GB
License
fair-noncommercial-research-license
Compare this model →

Xiaomi MiMo · Downloadable

MiMo-V2-Flash

Text generation

Generates text for conversations and writing.

Source listed
Dec 16, 2025
Parameters
309.8B
4-bit weights only
≈ 154.9 GB
License
mit
Compare this model →

MiniMax · Downloadable

VTP-Large-f16d64

Capabilities unconfirmed

Turns content into numerical representations for semantic search and retrieval.

Source listed
Dec 16, 2025
Parameters
731.6M
4-bit weights only
≈ 0.4 GB
License
other
Compare this model →

MiniMax · Downloadable

VTP-Base-f16d64

Capabilities unconfirmed

Turns content into numerical representations for semantic search and retrieval.

Source listed
Dec 16, 2025
Parameters
295.6M
4-bit weights only
≈ 0.1 GB
License
other
Compare this model →

MiniMax · Downloadable

VTP-Small-f16d64

Capabilities unconfirmed

Turns content into numerical representations for semantic search and retrieval.

Source listed
Dec 16, 2025
Parameters
167.2M
4-bit weights only
≈ 0.1 GB
License
other
Compare this model →

Meta · Downloadable

pixio-vit5b16

Capabilities unconfirmed

Turns content into numerical representations for semantic search and retrieval.

Source listed
Dec 15, 2025
Parameters
5.4B
4-bit weights only
≈ 2.7 GB
License
fair-noncommercial-research-license
Compare this model →

Meta · Downloadable

pixio-vit1b16

Capabilities unconfirmed

Turns content into numerical representations for semantic search and retrieval.

Source listed
Dec 15, 2025
Parameters
1.4B
4-bit weights only
≈ 0.7 GB
License
fair-noncommercial-research-license
Compare this model →

Meta · Downloadable

pixio-vitl16

Capabilities unconfirmed

Turns content into numerical representations for semantic search and retrieval.

Source listed
Dec 15, 2025
Parameters
303.4M
4-bit weights only
≈ 0.2 GB
License
fair-noncommercial-research-license
Compare this model →

Meta · Downloadable

pixio-vitb16

Capabilities unconfirmed

Turns content into numerical representations for semantic search and retrieval.

Source listed
Dec 15, 2025
Parameters
85.9M
4-bit weights only
≈ 0 GB
License
fair-noncommercial-research-license
Compare this model →

Google · Downloadable

gemma-scope-2

Capabilities unconfirmed

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

Source listed
Dec 15, 2025
Parameters
Not reported
4-bit weights only
Not reported
License
cc-by-4.0
Compare this model →

Google · Downloadable

gemma-scope-2-27b-it

Capabilities unconfirmed

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

Source listed
Dec 15, 2025
Parameters
27B
4-bit weights only
≈ 13.5 GB
License
cc-by-4.0
Compare this model →

Google · Downloadable

gemma-scope-2-27b-pt

Capabilities unconfirmed

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

Source listed
Dec 15, 2025
Parameters
27B
4-bit weights only
≈ 13.5 GB
License
cc-by-4.0
Compare this model →

Google · Downloadable

gemma-scope-2-12b-it

Capabilities unconfirmed

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

Source listed
Dec 15, 2025
Parameters
12B
4-bit weights only
≈ 6 GB
License
cc-by-4.0
Compare this model →

Google · Downloadable

gemma-scope-2-12b-pt

Capabilities unconfirmed

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

Source listed
Dec 15, 2025
Parameters
12B
4-bit weights only
≈ 6 GB
License
cc-by-4.0
Compare this model →

Google · Downloadable

gemma-scope-2-4b-it

Capabilities unconfirmed

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

Source listed
Dec 15, 2025
Parameters
4B
4-bit weights only
≈ 2 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.