utMistral AI · Downloadable
Voxtral-Mini-4B-Realtime-2602
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 21, 2026
- Parameters
- 4B
- 4-bit weights only
- ≈ 2 GB
- License
- apache-2.0
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 11, 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
1,399 dated recordsMicrosoft · Downloadable
VibeVoice-ASR
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 21, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- mit
Qwen · Alibaba · Downloadable
Qwen3-TTS-12Hz-0.6B-Base
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 21, 2026
- Parameters
- 600M
- 4-bit weights only
- ≈ 0.3 GB
- License
- apache-2.0
Qwen · Alibaba · Downloadable
Qwen3-TTS-12Hz-0.6B-CustomVoice
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 21, 2026
- Parameters
- 600M
- 4-bit weights only
- ≈ 0.3 GB
- License
- apache-2.0
Qwen · Alibaba · Downloadable
Qwen3-TTS-12Hz-1.7B-Base
A specialized research model. See the model card for its intended task and supported setup.
- Source listed
- Jan 21, 2026
- Parameters
- 1.7B
- 4-bit weights only
- ≈ 0.9 GB
- License
- apache-2.0
Qwen · Alibaba · Downloadable
Qwen3-TTS-12Hz-1.7B-CustomVoice
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 21, 2026
- Parameters
- 1.7B
- 4-bit weights only
- ≈ 0.9 GB
- License
- apache-2.0
Qwen · Alibaba · Downloadable
Qwen3-TTS-Tokenizer-12Hz
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 21, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- apache-2.0
Qwen · Alibaba · Downloadable
Qwen3-TTS-12Hz-1.7B-VoiceDesign
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 21, 2026
- Parameters
- 1.7B
- 4-bit weights only
- ≈ 0.9 GB
- License
- apache-2.0
Z.ai · Downloadable
GLM-4.7-Flash
Generates text for conversations and writing.
- Source listed
- Jan 19, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- mit
Google · Downloadable
alphagenome-fold-3
A specialized research model. See the model card for its intended task and supported setup.
- Source listed
- Jan 16, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- other
Google · Downloadable
alphagenome-fold-2
A specialized research model. See the model card for its intended task and supported setup.
- Source listed
- Jan 16, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- other
Google · Downloadable
alphagenome-fold-1
A specialized research model. See the model card for its intended task and supported setup.
- Source listed
- Jan 16, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- other
Google · Downloadable
alphagenome-fold-0
A specialized research model. See the model card for its intended task and supported setup.
- Source listed
- Jan 15, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- other
Black Forest Labs · Downloadable
FLUX.2-klein-4b
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jan 14, 2026
- Parameters
- 4B
- 4-bit weights only
- ≈ 2 GB
- License
- apache-2.0
Black Forest Labs · Downloadable
FLUX.2-klein-base-4b
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jan 14, 2026
- Parameters
- 4B
- 4-bit weights only
- ≈ 2 GB
- License
- apache-2.0
Black Forest Labs · Downloadable
FLUX.2-klein-9b
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jan 14, 2026
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Black Forest Labs · Downloadable
FLUX.2-klein-base-9b
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jan 14, 2026
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Google · Downloadable
alphagenome-all-folds
A specialized research model. See the model card for its intended task and supported setup.
- Source listed
- Jan 14, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- other
Black Forest Labs · Downloadable
FLUX.2-klein-4B
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jan 14, 2026
- Parameters
- 4B
- 4-bit weights only
- ≈ 2 GB
- License
- apache-2.0
Black Forest Labs · Downloadable
FLUX.2-klein-base-4B
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jan 14, 2026
- Parameters
- 4B
- 4-bit weights only
- ≈ 2 GB
- License
- apache-2.0
Black Forest Labs · Downloadable
FLUX.2-klein-base-9B
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jan 14, 2026
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Black Forest Labs · Downloadable
FLUX.2-klein-9B
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jan 14, 2026
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Microsoft · Downloadable
colipri
A specialized research model. See the model card for its intended task and supported setup.
- Source listed
- Jan 14, 2026
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- mit
Google · Downloadable
translategemma-27b-it
Understands text and images and responds in text.
- Source listed
- Jan 12, 2026
- Parameters
- 27B
- 4-bit weights only
- ≈ 13.5 GB
- License
- gemma
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.