Models 18
Latest releases first. Find a model for what you’re making.
18 matching modelsClear filters
0–7d New 8–30d Recent 31d+ Older · days since release
Yue2-3B-GGUF
10d57.6K downloads / mo68 likesConfucius4-R2T2
10d253 downloads / mo71 likesYuE2-3B
11d13.7K downloads / mo821 likesorukeet
11d10.6K downloads / mo64 likesrumik-oss-1
14d2.1K downloads / mo60 likesIrodori-TTS-v4.1-Anime
16d0 downloads / mo121 likesVibeVoice-ASR-Streaming-7B
18d5.9K downloads / mo242 likesBreeze-TTS-2
26d10.9K downloads / mo583 likesAuK-Flash
30d2.3K downloads / mo92 likesAuK
33d3.2K downloads / mo308 likesInkling Small
52dInkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.
489.5K downloads / mo408 likesInkling
65dInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
336.1K downloads / mo1.8K likesNemotron 3 Nano Omni (free)
145dNVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems.
272.4K downloads / mo427 likesMiMo-V2.5
151dMiMo-V2.5 is a native omnimodal model by Xiaomi.
296.7K downloads / mo424 likesVoxtral Small 24B 2507
325dVoxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance.
77.9K downloads / mo524 likesspeaker-diarization-community-1
523d5.2M downloads / mo1.9K likesKokoro-82M
633d11.7M downloads / mo7K likesspeaker-diarization-3.1
1039d8.2M downloads / mo3.7K likes
