Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

AX BI selected AXQ Qwen and Nemotron MLX MXFP4/MXFP8 packs with protected MTP. Development artifacts; see individual model cards.

AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP4-MTP

Text Generation • 35B • Updated 5 days ago • 37
AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP8-MTP

Text Generation • 35B • Updated 5 days ago • 33
AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP4-MTP

Text Generation • 9B • Updated 5 days ago • 37
AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP8-MTP

Text Generation • 9B • Updated 5 days ago • 32

AuK (Tencent Hunyuan) for MLX

AuK speech generation + editing for mlx-auk-swift. DiT/VAE MIT; required Qwen2.5-Omni encoder is Qwen Research (NC).

mlx-community/AuK-Flash-bf16

Text-to-Speech • Updated 5 days ago • 101
mlx-community/AuK-bf16

Text-to-Speech • Updated 5 days ago • 105
mlx-community/Qwen2.5-Omni-3B-Thinker-bf16

Updated 5 days ago • 60
mlx-community/Qwen2.5-Omni-3B-Thinker-8bit

Updated 5 days ago • 161 • 1

Those video gen tools

Running

79

Uncensored Image-to-Video Alchemist 🔥

🐳

79

Generate videos from your images with AI prompts

Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis

Paper • 2504.01960 • Published Apr 2, 2025

Alkove 1-preview

On-device voice input: voice isolation, voice activity, wake words, voiceprints, text to phonemes. Apache-2.0, under 8 MB for all five.

Running

Alkove demo

🎧

Voice isolation and keyword spotting in the browser
alkove-ai/alkove-focus-1-preview

Audio-to-Audio • Updated 3 days ago
alkove-ai/alkove-spot-1-preview

Audio Classification • Updated 3 days ago
alkove-ai/alkove-timbre-1-preview

Audio Classification • Updated 3 days ago

SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF

Image-Text-to-Text • 177B • Updated 20 days ago • 2.12M • 379

ozgurguler/ahenk-tts-tr

Text-to-Speech • Updated 7 days ago • 19

Running on Zero

Agents

Featured

145

MiniMax-H3 Character Swap LoRA

🎭

145

Swap one character in a clip for a reference character
Running on Zero

Agents

Featured

1.43k

OmniVoice

🌍

1.43k

High-quality voice cloning TTS for 600+ languages
Running

79

Uncensored Image-to-Video Alchemist 🔥

🐳

79

Generate videos from your images with AI prompts

Tɛkyerɛma: Ghanaian language models

What the Tɛkyerɛma app and language service run: translate, hear and speak Twi, Ewe, Hausa, Dagbani, Kusaal and Ghanaian English.

Running on Zero

Agents

2

Tekyerema Language Service

🧵

2

Hear, speak and translate Ghanaian languages
PrinceAlhassanNasamu/tekyerema-nllb600m-v3

Translation • 0.6B • Updated 5 days ago • 44
PrinceAlhassanNasamu/tekyerema-ghen-f5

Text-to-Speech • Updated about 14 hours ago • 130
PrinceAlhassanNasamu/tekyerema-tts-twi

Text-to-Speech • 83M • Updated 5 days ago • 74

AX BI selected AXQ Qwen and Nemotron MLX MXFP4/MXFP8 packs with protected MTP. Development artifacts; see individual model cards.

AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP4-MTP

Text Generation • 35B • Updated 5 days ago • 37
AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP8-MTP

Text Generation • 35B • Updated 5 days ago • 33
AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP4-MTP

Text Generation • 9B • Updated 5 days ago • 37
AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP8-MTP

Text Generation • 9B • Updated 5 days ago • 32

SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF

Image-Text-to-Text • 177B • Updated 20 days ago • 2.12M • 379

AuK (Tencent Hunyuan) for MLX

AuK speech generation + editing for mlx-auk-swift. DiT/VAE MIT; required Qwen2.5-Omni encoder is Qwen Research (NC).

mlx-community/AuK-Flash-bf16

Text-to-Speech • Updated 5 days ago • 101
mlx-community/AuK-bf16

Text-to-Speech • Updated 5 days ago • 105
mlx-community/Qwen2.5-Omni-3B-Thinker-bf16

Updated 5 days ago • 60
mlx-community/Qwen2.5-Omni-3B-Thinker-8bit

Updated 5 days ago • 161 • 1

ozgurguler/ahenk-tts-tr

Text-to-Speech • Updated 7 days ago • 19

Those video gen tools

Running

79

Uncensored Image-to-Video Alchemist 🔥

🐳

79

Generate videos from your images with AI prompts

Running on Zero

Agents

Featured

145

MiniMax-H3 Character Swap LoRA

🎭

145

Swap one character in a clip for a reference character
Running on Zero

Agents

Featured

1.43k

OmniVoice

🌍

1.43k

High-quality voice cloning TTS for 600+ languages
Running

79

Uncensored Image-to-Video Alchemist 🔥

🐳

79

Generate videos from your images with AI prompts

Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis

Paper • 2504.01960 • Published Apr 2, 2025

Alkove 1-preview

On-device voice input: voice isolation, voice activity, wake words, voiceprints, text to phonemes. Apache-2.0, under 8 MB for all five.

Running

Alkove demo

🎧

Voice isolation and keyword spotting in the browser
alkove-ai/alkove-focus-1-preview

Audio-to-Audio • Updated 3 days ago
alkove-ai/alkove-spot-1-preview

Audio Classification • Updated 3 days ago
alkove-ai/alkove-timbre-1-preview

Audio Classification • Updated 3 days ago

Tɛkyerɛma: Ghanaian language models

What the Tɛkyerɛma app and language service run: translate, hear and speak Twi, Ewe, Hausa, Dagbani, Kusaal and Ghanaian English.

Running on Zero

Agents

2

Tekyerema Language Service

🧵

2

Hear, speak and translate Ghanaian languages
PrinceAlhassanNasamu/tekyerema-nllb600m-v3

Translation • 0.6B • Updated 5 days ago • 44
PrinceAlhassanNasamu/tekyerema-ghen-f5

Text-to-Speech • Updated about 14 hours ago • 130
PrinceAlhassanNasamu/tekyerema-tts-twi

Text-to-Speech • 83M • Updated 5 days ago • 74

Previous
1
...
218
219
220
221
222
...
24,242
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs