1,226 models · 1,226 open weights · 200 API-only · refreshed nightly

Open-weights models

Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.

All 1,426 Open weights (self-host) 1,226 API-only 200

All text-generation 534 text-to-image 155 image-text-to-text 112 ASR 86 sentence-similarity 64 translation 56 text-classification 51 feature-extraction 48 image-classification 39 token-classification 21 text-to-speech 19 audio-classification 12 image-segmentation 11 summarization 8 object-detection 8 audio-text-to-text 1 any-to-any 1

Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB

19 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	Kokoro-82M hexgrad · text-to-speech Open weights	82 M	—	✓ apache-2.0	10.1 M	from 0.7 GB
02	audio.cpp-gguf audio-cpp · text-to-speech Open weights	—	—	other	6.6 M	from 1.6 GB
03	XTTS-v2 coqui · text-to-speech Open weights	—	—	other	6.1 M	—
04	OmniVoice k2-fsa · text-to-speech Open weights	610 M	—	unknown	2.0 M	from 4.2 GB
05	Qwen3-TTS-12Hz-1.7B-CustomVoice Qwen · text-to-speech Open weights	1.9 B	—	✓ apache-2.0	1.9 M	from 5.8 GB
06	chatterbox ResembleAI · text-to-speech Open weights	—	—	✓ mit	1.8 M	from 12.2 GB
07	VieNeu-TTS-v3-Turbo pnnbao-ump · text-to-speech Open weights	131 M	1 K	✓ apache-2.0	1.4 M	from 0.7 GB
08	kokoro-inno-clone-tuner remsky · text-to-speech Open weights	9.7 M	—	✓ apache-2.0	1.2 M	from 0.5 GB
09	VoxCPM2 openbmb · text-to-speech Open weights	2.3 B	—	✓ apache-2.0	925 K	from 5.9 GB
10	F5-TTS SWivid · text-to-speech Open weights	—	—	✗ cc-by-nc-4.0	883 K	from 5.0 GB
11	Qwen3-TTS-12Hz-0.6B-CustomVoice Qwen · text-to-speech Open weights	910 M	—	✓ apache-2.0	871 K	from 3.4 GB
12	Kokoro-82M-v1.0-ONNX onnx-community · text-to-speech Open weights	82 M	—	✓ apache-2.0	680 K	from 0.7 GB
13	Qwen3-TTS-12Hz-0.6B-Base Qwen · text-to-speech Open weights	910 M	—	✓ apache-2.0	625 K	from 3.4 GB
14	Qwen3-TTS-GGUF Serveurperso · text-to-speech Open weights	—	—	✓ apache-2.0	530 K	from 1.8 GB
15	Higgs-Audio-v3-Studio drbaph · text-to-speech Open weights	—	—	other	498 K	from 5.0 GB
16	sanoTTS ampixa · text-to-speech Open weights	—	—	gpl-3.0	473 K	from 0.5 GB
17	Qwen3-TTS-12Hz-1.7B-VoiceDesign Qwen · text-to-speech Open weights	1.9 B	—	✓ apache-2.0	423 K	from 5.8 GB
18	higgs-tts-2-3b-base bosonai · text-to-speech Open weights	5.8 B	2 K	other	415 K	from 14.1 GB
19	VibeVoice-1.5B microsoft · text-to-speech Open weights	2.7 B	—	✓ mit	401 K	from 6.9 GB

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.