1,011 models · refreshed nightly

Feature extraction models

Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

All text-generation 400 text-to-image 150 ASR 89 image-text-to-text 82 sentence-similarity 55 feature-extraction 47 translation 44 text-classification 39 image-classification 32 token-classification 22 text-to-speech 16 audio-classification 12 image-segmentation 8 object-detection 8 summarization 7

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

47 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	bge-small-en-v1.5 BAAI · feature-extraction	30 M	512	✓ mit	72.4 M	from 0.7 GB
02	bge-large-en-v1.5 BAAI · feature-extraction	340 M	512	✓ mit	13.1 M	from 2.0 GB
03	bge-base-en-v1.5 BAAI · feature-extraction	110 M	512	✓ mit	10.0 M	from 1.0 GB
04	Qwen3-Embedding-0.6B Qwen · feature-extraction	600 M	33 K	✓ apache-2.0	9.8 M	from 1.9 GB
05	multilingual-e5-large intfloat · feature-extraction	560 M	512	✓ mit	7.5 M	from 3.0 GB
06	mxbai-embed-large-v1 mixedbread-ai · feature-extraction	340 M	512	✓ apache-2.0	4.9 M	from 1.3 GB
07	bge-small-zh-v1.5 BAAI · feature-extraction	20 M	512	✓ mit	4.8 M	from 0.6 GB
08	granite-embedding-small-english-r2 ibm-granite · feature-extraction	50 M	8 K	✓ apache-2.0	3.8 M	from 0.6 GB
09	Qwen3-Embedding-4B Qwen · feature-extraction	4.0 B	41 K	✓ apache-2.0	3.4 M	from 10.0 GB
10	Qwen3-Embedding-8B Qwen · feature-extraction	7.6 B	41 K	✓ apache-2.0	3.3 M	from 18.3 GB
11	jina-embeddings-v3 jinaai · feature-extraction	570 M	8 K	✗ cc-by-nc-4.0	3.2 M	from 1.8 GB
12	all-MiniLM-L6-v2 Xenova · feature-extraction	—	512	✓ apache-2.0	2.9 M	—
13	bge-reranker-large BAAI · feature-extraction	560 M	512	✓ mit	2.4 M	from 3.0 GB
14	multilingual-e5-large-instruct intfloat · feature-extraction	560 M	512	✓ mit	2.3 M	from 1.8 GB
15	bge-base-en-v1.5 Xenova · feature-extraction	—	512	✓ mit	2.2 M	—
16	bge-large-zh-v1.5 BAAI · feature-extraction	—	512	✓ mit	1.8 M	—
17	bge-base-zh-v1.5 BAAI · feature-extraction	—	512	✓ mit	1.7 M	—
18	SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction	110 M	512	✓ apache-2.0	1.6 M	from 1.0 GB
19	bge-small-en BAAI · feature-extraction	30 M	512	✓ mit	1.6 M	from 0.7 GB
20	w2v-bert-2.0 facebook · feature-extraction	580 M	—	✓ mit	1.4 M	from 3.1 GB
21	bge-multilingual-gemma2 BAAI · feature-extraction	9.2 B	8 K	⚠ gemma	1.1 M	from 42.5 GB
22	1 unslothai · feature-extraction	—	2 K	unknown	1.1 M	from 0.5 GB
23	bge-small-en-v1.5 michaelfeil · feature-extraction	30 M	512	✓ mit	1.1 M	from 0.7 GB
24	jina-embeddings-v2-small-en jinaai · feature-extraction	30 M	8 K	✓ apache-2.0	1.0 M	from 0.6 GB
25	repeat unslothai · feature-extraction	—	—	unknown	975 K	from 0.5 GB
26	UAE-Large-V1 WhereIsAI · feature-extraction	340 M	512	✓ mit	928 K	from 2.0 GB
27	hubert-base-ls960 facebook · feature-extraction	—	—	✓ apache-2.0	904 K	—
28	wavlm-base-plus microsoft · feature-extraction	—	—	unknown	902 K	—
29	specter2_base allenai · feature-extraction	—	512	✓ apache-2.0	873 K	—
30	llama-nemotron-embed-1b-v2 nvidia · feature-extraction	1.2 B	131 K	other	828 K	from 3.4 GB
31	mimi kyutai · feature-extraction	100 M	8 K	✓ cc-by-4.0	798 K	from 0.9 GB
32	clap-htsat-unfused laion · feature-extraction	—	—	✓ apache-2.0	742 K	—
33	larger_clap_music_and_speech laion · feature-extraction	—	—	✓ apache-2.0	680 K	—
34	indobert-base-p1 indobenchmark · feature-extraction	—	512	✓ mit	670 K	—
35	splade-cocondenser-ensembledistil naver · feature-extraction	—	512	✗ cc-by-nc-sa-4.0	641 K	—
36	conv-bert-base YituTech · feature-extraction	—	512	unknown	603 K	—
37	encodec_24khz facebook · feature-extraction	20 M	—	unknown	577 K	from 0.6 GB
38	sentence-bert-base-ja-mean-tokens-v2 sonoisa · feature-extraction	110 M	512	cc-by-sa-4.0	575 K	from 1.0 GB
39	Qwen3-Embedding-4B-W4A16-G128 boboliu · feature-extraction	4.1 B	41 K	✓ apache-2.0	532 K	from 4.0 GB
40	jina-clip-v2 jinaai · feature-extraction	870 M	—	✗ cc-by-nc-4.0	530 K	from 2.5 GB
41	wavlm-large microsoft · feature-extraction	—	—	unknown	521 K	—
42	jina-embeddings-v5-text-nano jinaai · feature-extraction	210 M	8 K	✗ cc-by-nc-4.0	515 K	from 1.1 GB
43	lambda unslothai · feature-extraction	—	—	unknown	504 K	from 0.5 GB
44	vram-16 unslothai · feature-extraction	—	—	unknown	462 K	from 0.5 GB
45	pplx-embed-v1-0.6b perplexity-ai · feature-extraction	600 M	33 K	✓ mit	461 K	from 3.2 GB
46	bge-base-en BAAI · feature-extraction	110 M	512	✓ mit	460 K	from 1.0 GB
47	e5-mistral-7b-instruct intfloat · feature-extraction	7.1 B	33 K	✓ mit	460 K	from 17.2 GB

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.