1,213 models · 1,213 open weights · 210 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 1,423 Open weights (self-host) 1,213 API-only 210

All text-generation 539 text-to-image 155 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 token-classification 22 text-to-speech 19 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 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

654 models

#	Model	Params	Context	Commercial use	30d	On RTX 4070 · 16 GB
101	resnet50.a1_in1k timm · image-classification Open weights	30 M	—	✓ apache-2.0	1.6 M	0.6 GB
102	Qwen2.5-7B-Instruct-AWQ Qwen · text-generation Open weights	7.6 B	33 K	✓ apache-2.0	1.6 M	7.8 GB
103	Ternary-Bonsai-2-27B-gguf prism-ml · text-generation Open weights Also via API	27.0 B	—	✓ apache-2.0	1.6 M	5.2 GB
104	Qwen3.6-35B-A3B-GGUF unsloth · image-text-to-text Open weights	—	—	✓ apache-2.0	1.6 M	11.6 GB
105	nsfw_image_detection Falconsai · image-classification Open weights	90 M	—	✓ apache-2.0	1.6 M	0.9 GB
106	Qwen-Image-2.1-GGUF unsloth · text-to-image Open weights	7.1 B	—	other	1.6 M	4.3 GB
107	Qwen3-8B-AWQ Qwen · text-generation Open weights	8.2 B	41 K	✓ apache-2.0	1.6 M	8.4 GB
108	Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF ukisai · text-generation Open weights	27.0 B	—	other	1.6 M	4.6 GB
109	kokoro-inno-clone-tuner remsky · text-to-speech Open weights	9.7 M	—	✓ apache-2.0	1.6 M	0.5 GB
110	Qwen3.5-4B-GGUF unsloth · image-text-to-text Open weights	—	—	✓ apache-2.0	1.5 M	2.8 GB
111	paraphrase-MiniLM-L6-v2 sentence-transformers · sentence-similarity Open weights	20 M	512	✓ apache-2.0	1.5 M	0.6 GB
112	Qwen3-VL-8B-Instruct-FP8 Qwen · image-text-to-text Open weights	8.8 B	—	✓ apache-2.0	1.5 M	13.5 GB
113	Qwen3-4B-Instruct-2507-FP8 Qwen · text-generation Open weights	4.4 B	262 K	✓ apache-2.0	1.5 M	6.9 GB
114	distilgpt2 distilbert · text-generation Open weights	90 M	—	✓ apache-2.0	1.5 M	0.9 GB
115	jina-embeddings-v3 jinaai · feature-extraction Open weights	570 M	8 K	✗ cc-by-nc-4.0	1.5 M	1.8 GB
116	multi-qa-mpnet-base-dot-v1 sentence-transformers · sentence-similarity Open weights	110 M	512	unknown	1.5 M	1.0 GB
117	SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction Open weights	110 M	512	✓ apache-2.0	1.4 M	1.0 GB
118	Qwen3-TTS-12Hz-1.7B-CustomVoice Qwen · text-to-speech Open weights	1.9 B	—	✓ apache-2.0	1.4 M	5.8 GB
119	Dirk-Qwen3.8-27B-GGUF peculiar-ragdoll · image-text-to-text Open weights	27.0 B	—	✓ apache-2.0	1.4 M	14.2 GB
120	chandra-ocr-2 datalab-to · image-text-to-text Open weights	5.3 B	—	⚠ openrail	1.4 M	12.9 GB
121	Qwen2.5-3B-Instruct-AWQ Qwen · text-generation Open weights	3.4 B	33 K	other	1.4 M	4.0 GB
122	wav2vec2-xls-r-300m-cs-250 comodoro · ASR Open weights	320 M	—	✓ apache-2.0	1.4 M	1.9 GB
123	rtdetr_r101vd_coco_o365 PekingU · object-detection Open weights	80 M	—	✓ apache-2.0	1.4 M	0.9 GB
124	Qwen3.8-27B-GSQ-RCO-GGUF ISTA-DASLab · image-text-to-text Open weights	—	—	✓ apache-2.0	1.4 M	1.5 GB
125	Qwen-Image-2.1-Turbo-GGUF unsloth · text-to-image Open weights	—	—	other	1.4 M	3.2 GB
126	gender-classification rizvandwiki · image-classification Open weights	90 M	—	unknown	1.3 M	0.9 GB
127	Llama-3.2-1B-Instruct meta-llama · text-generation · gated Open weights Also via API	1.2 B	—	⚠ llama3.2	1.3 M	3.4 GB
128	ko-sroberta-multitask jhgan · sentence-similarity Open weights	110 M	512	unknown	1.3 M	1.0 GB
129	w2v-bert-2.0 facebook · feature-extraction Open weights	580 M	—	✓ mit	1.3 M	3.1 GB
130	Qwen2.5-VL-7B-Instruct-AWQ Qwen · image-text-to-text Open weights	8.3 B	128 K	✓ apache-2.0	1.3 M	9.4 GB
131	wav2vec2-large-voxrex-swedish KBLab · ASR Open weights	320 M	—	✓ cc0-1.0	1.3 M	1.9 GB
132	table-transformer-structure-recognition microsoft · object-detection Open weights	30 M	1 K	✓ mit	1.3 M	0.6 GB
133	F5-TTS SWivid · text-to-speech Open weights	—	—	✗ cc-by-nc-4.0	1.3 M	5.0 GB
134	Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive HauhauCS · image-text-to-text Open weights	—	—	✓ apache-2.0	1.3 M	13.3 GB
135	Ornith-1.5-397B-GGUF ornith-ai · text-generation Open weights	—	—	✓ mit	1.3 M	1.5 GB
136	jina-embeddings-v2-small-en jinaai · feature-extraction Open weights	30 M	8 K	✓ apache-2.0	1.3 M	0.6 GB
137	efficientvit_l2.r288_in1k timm · image-classification Open weights	64 M	—	✓ apache-2.0	1.3 M	0.8 GB
138	Qwen3-ASR-1.7B-gguf handy-computer · ASR Open weights	1.7 B	—	✓ apache-2.0	1.2 M	2.2 GB
139	cohere-transcribe-03-2026-gguf handy-computer · ASR Open weights	2.1 B	—	✓ apache-2.0	1.2 M	2.5 GB
140	Qwen2.5-VL-7B-Instruct-NVFP4 nvidia · text-generation Open weights	5.0 B	128 K	other	1.2 M	9.2 GB
141	Llama-3.2-1B-Instruct unsloth · text-generation Open weights	1.2 B	131 K	⚠ llama3.2	1.2 M	3.4 GB
142	Qwen3-TTS-GGUF Serveurperso · text-to-speech Open weights	—	—	✓ apache-2.0	1.2 M	1.8 GB
143	romanian-wav2vec2 gigant · ASR Open weights	320 M	—	✓ apache-2.0	1.2 M	1.9 GB
144	Qwen2.5-0.5B Qwen · text-generation Open weights	490 M	33 K	✓ apache-2.0	1.2 M	1.7 GB
145	Ternary-Bonsai-2-9B-gguf prism-ml · image-text-to-text Open weights Also via API	9.0 B	—	✓ apache-2.0	1.2 M	2.9 GB
146	embeddinggemma-300m google · sentence-similarity · gated Open weights	300 M	—	⚠ gemma	1.2 M	1.9 GB
147	parakeet-tdt-0.6b-v3-gguf handy-computer · ASR Open weights	600 M	—	✓ cc-by-4.0	1.1 M	1.1 GB
148	Qwen2.5-14B-Instruct-AWQ Qwen · text-generation Open weights	14.8 B	33 K	✓ apache-2.0	1.1 M	13.7 GB
149	wav2vec2-large-xlsr-korean kresnik · ASR Open weights	320 M	—	✓ apache-2.0	1.1 M	1.9 GB
150	Qwen3-0.6B PrimeIntellect · text-generation Open weights	752 M	41 K	✓ apache-2.0	1.1 M	2.3 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.