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 28, 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

Meta · Downloadable

sapiens2-pose-0.4b

Keypoint detection

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

Source listed: Apr 23, 2026
Parameters: 400M
4-bit weights only: ≈ 0.2 GB
License: other

Compare this model →

inclusionAI · Downloadable

LLaDA2.0-Uni

Image generationImage editingEmbeddings

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: Apr 22, 2026
Parameters: 16.3B
4-bit weights only: ≈ 8.2 GB
License: apache-2.0

Compare this model →

NVIDIA · Downloadable

Kumo-Anomaly

Capabilities unconfirmed

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

Source listed: Apr 21, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

NVIDIA · Downloadable

nv-tesseract-ad-diffusion

Capabilities unconfirmed

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

Source listed: Apr 21, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Moondream · Downloadable

tracking

Capabilities unconfirmed

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

Source listed: Apr 19, 2026
Parameters: 194.2M
4-bit weights only: ≈ 0.1 GB
License: Not disclosed

Compare this model →

OpenAI · Downloadable

privacy-filter

Token classification

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

Source listed: Apr 17, 2026
Parameters: 1.4B
4-bit weights only: ≈ 0.7 GB
License: apache-2.0

Compare this model →

Kyutai · Downloadable

moshi-rag-artifacts

Capabilities unconfirmed

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

Source listed: Apr 15, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: Not disclosed

Compare this model →

Microsoft · Downloadable

skala-baselines

Capabilities unconfirmed

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

Source listed: Apr 13, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: mit

Compare this model →

Microsoft · Downloadable

skala-1.0

Capabilities unconfirmed

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

Source listed: Apr 13, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: mit

Compare this model →

Microsoft · Downloadable

skala-1.1

Capabilities unconfirmed

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

Source listed: Apr 13, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: mit

Compare this model →

Tencent · Downloadable

DisCa

Capabilities unconfirmed

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

Source listed: Apr 9, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: Not disclosed

Compare this model →

Google · Downloadable

tipsv2-g14-dpt

VisionImage segmentationDepth estimationEmbeddings

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

Source listed: Apr 9, 2026
Parameters: 1.3B
4-bit weights only: ≈ 0.7 GB
License: apache-2.0

Compare this model →

Google · Downloadable

tipsv2-so400m14-dpt

VisionImage segmentationDepth estimationEmbeddings

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

Source listed: Apr 9, 2026
Parameters: 532.9M
4-bit weights only: ≈ 0.3 GB
License: apache-2.0

Compare this model →

Google · Downloadable

tipsv2-l14-dpt

VisionImage segmentationDepth estimationEmbeddings

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

Source listed: Apr 9, 2026
Parameters: 405.7M
4-bit weights only: ≈ 0.2 GB
License: apache-2.0

Compare this model →

Google · Downloadable

tipsv2-b14-dpt

VisionImage segmentationDepth estimationEmbeddings

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

Source listed: Apr 9, 2026
Parameters: 158M
4-bit weights only: ≈ 0.1 GB
License: apache-2.0

Compare this model →

Google · Downloadable

tipsv2-g14

VisionImage classificationEmbeddings

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

Source listed: Apr 9, 2026
Parameters: 1.5B
4-bit weights only: ≈ 0.8 GB
License: apache-2.0

Compare this model →

Google · Downloadable

tipsv2-so400m14

VisionImage classificationEmbeddings

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

Source listed: Apr 9, 2026
Parameters: 861.7M
4-bit weights only: ≈ 0.4 GB
License: apache-2.0

Compare this model →

Google · Downloadable

tipsv2-b14

VisionImage classificationEmbeddings

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

Source listed: Apr 9, 2026
Parameters: 195.9M
4-bit weights only: ≈ 0.1 GB
License: apache-2.0

Compare this model →

Google · Downloadable

tipsv2-l14

VisionImage classificationEmbeddings

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

Source listed: Apr 9, 2026
Parameters: 487.9M
4-bit weights only: ≈ 0.2 GB
License: apache-2.0

Compare this model →

NVIDIA · Downloadable

GEAR-CHIP

Capabilities unconfirmed

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

Source listed: Apr 8, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: Not disclosed

Compare this model →

NVIDIA · Downloadable

TMR-SOMA-RP-v1

Capabilities unconfirmed

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

Source listed: Apr 8, 2026
Parameters: Not reported
4-bit weights only: Not reported
License: other

Compare this model →

NVIDIA · Downloadable

Kimodo-SOMA-SEED-v1.1

Capabilities unconfirmed

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

Source listed: Apr 7, 2026
Parameters: 283.3M
4-bit weights only: ≈ 0.1 GB
License: other

Compare this model →

NVIDIA · Downloadable

Kimodo-SOMA-RP-v1.1

Capabilities unconfirmed

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

Source listed: Apr 7, 2026
Parameters: 283.3M
4-bit weights only: ≈ 0.1 GB
License: other

Compare this model →

NVIDIA · Downloadable

Kumo-Forecast

Capabilities unconfirmed

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

Source listed: Apr 7, 2026
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.