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 Sep 10, 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

440 dated records

DeepSeek · Downloadable

Janus-Pro-7B

Image generation

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

Source listed: Jan 26, 2025
Parameters: 7B
4-bit weights only: ≈ 3.5 GB
License: mit

Compare this model →

Mistral AI · Downloadable

Mistral-Small-24B-Base-2501

Capabilities unconfirmed

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

Source listed: Jan 23, 2025
Parameters: 24B
4-bit weights only: ≈ 12 GB
License: apache-2.0

Compare this model →

Microsoft · Downloadable

distilled_decoding

Capabilities unconfirmed

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

Source listed: Jan 11, 2025
Parameters: Not reported
4-bit weights only: Not reported
License: mit

Compare this model →

DeepSeek · Downloadable

DeepSeek-V3-Base

Capabilities unconfirmed

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

Source listed: Dec 25, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: Not disclosed

Compare this model →

Microsoft · Downloadable

LLM2CLIP-Llama3.2-1B-EVA02-L-14-336

Capabilities unconfirmed

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

Source listed: Dec 11, 2024
Parameters: 1B
4-bit weights only: ≈ 0.5 GB
License: apache-2.0

Compare this model →

Z.ai · Downloadable

webrl-orm-llama-3.1-8b

Capabilities unconfirmed

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

Source listed: Dec 9, 2024
Parameters: 8B
4-bit weights only: ≈ 4 GB
License: Not disclosed

Compare this model →

Microsoft · Downloadable

VidTok

Video generation

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

Source listed: Dec 8, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: mit

Compare this model →

Z.ai · Downloadable

MathGLM-Vision-19B

Capabilities unconfirmed

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

Source listed: Dec 5, 2024
Parameters: 19B
4-bit weights only: ≈ 9.5 GB
License: apache-2.0

Compare this model →

Z.ai · Downloadable

MathGLM-Vision

Capabilities unconfirmed

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

Source listed: Dec 5, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Microsoft · Downloadable

LLM2CLIP-Llama3.2-1B-EVA02-L-14-224

Capabilities unconfirmed

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

Source listed: Nov 30, 2024
Parameters: 1B
4-bit weights only: ≈ 0.5 GB
License: mit

Compare this model →

Microsoft · Downloadable

LLM2CLIP-Llama-3.2-1B-Instruct-CC-Finetuned

Capabilities unconfirmed

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

Source listed: Nov 30, 2024
Parameters: 1B
4-bit weights only: ≈ 0.5 GB
License: mit

Compare this model →

Black Forest Labs · Downloadable

FLUX.1-Depth-dev-lora

Image generation

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

Source listed: Nov 20, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: other

Compare this model →

Black Forest Labs · Downloadable

FLUX.1-Canny-dev-lora

Image generation

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

Source listed: Nov 20, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: other

Compare this model →

Black Forest Labs · Downloadable

FLUX.1-Redux-dev

Image generation

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

Source listed: Nov 20, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: other

Compare this model →

Black Forest Labs · Downloadable

FLUX.1-Fill-dev

Image generation

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

Source listed: Nov 20, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: other

Compare this model →

Microsoft · Downloadable

LLM2CLIP-Openai-L-14-224

Capabilities unconfirmed

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

Source listed: Nov 19, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: apache-2.0

Compare this model →

Microsoft · Downloadable

LLM2CLIP-Llama-3-8B-Instruct-CC-Finetuned

Capabilities unconfirmed

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

Source listed: Nov 16, 2024
Parameters: 8B
4-bit weights only: ≈ 4 GB
License: apache-2.0

Compare this model →

Mistral AI · Downloadable

Pixtral-Large-Instruct-2411

Capabilities unconfirmed

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

Source listed: Nov 14, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: other

Compare this model →

Mistral AI · Downloadable

Mistral-Large-Instruct-2411

Capabilities unconfirmed

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

Source listed: Nov 14, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: other

Compare this model →

DeepSeek · Downloadable

JanusFlow-1.3B

Image generation

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

Source listed: Nov 12, 2024
Parameters: 1.3B
4-bit weights only: ≈ 0.7 GB
License: mit

Compare this model →

Microsoft · Downloadable

Reducio-VAE

Video generation

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

Source listed: Nov 8, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: mit

Compare this model →

Microsoft · Downloadable

Phi-3-vision-128k-instruct-onnx

Capabilities unconfirmed

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

Source listed: Nov 8, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: mit

Compare this model →

Microsoft · Downloadable

Phi-3.5-vision-instruct-onnx

Capabilities unconfirmed

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

Source listed: Nov 8, 2024
Parameters: Not reported
4-bit weights only: Not reported
License: mit

Compare this model →

Microsoft · Downloadable

LLM2CLIP-Openai-B-16

Capabilities unconfirmed

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

Source listed: Nov 7, 2024
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.