1,054 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 410 text-to-image 153 ASR 92 image-text-to-text 89 sentence-similarity 61 feature-extraction 47 translation 47 text-classification 42 image-classification 34 token-classification 27 text-to-speech 12 audio-classification 11 object-detection 11 summarization 9 image-segmentation 9

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	64.5 M	from 0.7 GB
02	bge-large-en-v1.5 BAAI · feature-extraction	340 M	512	✓ mit	11.4 M	from 2.0 GB
03	bge-base-en-v1.5 BAAI · feature-extraction	110 M	512	✓ mit	10.5 M	from 1.0 GB
04	Qwen3-Embedding-0.6B Qwen · feature-extraction	600 M	33 K	✓ apache-2.0	8.6 M	from 1.9 GB
05	multilingual-e5-large intfloat · feature-extraction	560 M	512	✓ mit	7.2 M	from 3.0 GB
06	granite-embedding-small-english-r2 ibm-granite · feature-extraction	50 M	8 K	✓ apache-2.0	6.3 M	from 0.6 GB
07	bge-small-zh-v1.5 BAAI · feature-extraction	20 M	512	✓ mit	5.1 M	from 0.6 GB
08	all-MiniLM-L6-v2 Xenova · feature-extraction	20 M	512	✓ apache-2.0	3.0 M	from 0.5 GB
09	bge-reranker-large BAAI · feature-extraction	560 M	512	✓ mit	2.8 M	from 3.0 GB
10	Qwen3-Embedding-8B Qwen · feature-extraction	7.6 B	41 K	✓ apache-2.0	2.6 M	from 18.3 GB
11	bge-base-en-v1.5 Xenova · feature-extraction	110 M	512	✓ mit	2.5 M	from 0.8 GB
12	bge-base-en BAAI · feature-extraction	110 M	512	✓ mit	2.4 M	from 1.0 GB
13	mxbai-embed-large-v1 mixedbread-ai · feature-extraction	340 M	512	✓ apache-2.0	2.4 M	from 1.3 GB
14	w2v-bert-2.0 facebook · feature-extraction	580 M	—	✓ mit	2.2 M	from 3.1 GB
15	Qwen3-Embedding-4B Qwen · feature-extraction	4.0 B	41 K	✓ apache-2.0	2.1 M	from 10.0 GB
16	jina-embeddings-v3 jinaai · feature-extraction	570 M	8 K	✗ cc-by-nc-4.0	2.0 M	from 1.8 GB
17	multilingual-e5-large-instruct intfloat · feature-extraction	560 M	512	✓ mit	1.6 M	from 1.8 GB
18	SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction	110 M	512	✓ apache-2.0	1.5 M	from 1.0 GB
19	clap-htsat-unfused laion · feature-extraction	—	—	✓ apache-2.0	1.3 M	—
20	wavlm-large microsoft · feature-extraction	—	—	unknown	1.2 M	—
21	specter2_base allenai · feature-extraction	—	512	✓ apache-2.0	1.2 M	—
22	UAE-Large-V1 WhereIsAI · feature-extraction	340 M	512	✓ mit	1.1 M	from 2.0 GB
23	bge-large-zh-v1.5 BAAI · feature-extraction	—	512	✓ mit	1.1 M	—
24	1 unslothai · feature-extraction	—	2 K	unknown	1.0 M	from 0.5 GB
25	e5-mistral-7b-instruct-bnb-4bit gabor-hosu · feature-extraction	7.3 B	33 K	✓ mit	1.0 M	from 5.8 GB
26	wavlm-base-plus microsoft · feature-extraction	—	—	unknown	946 K	—
27	jina-embeddings-v2-small-en jinaai · feature-extraction	30 M	8 K	✓ apache-2.0	923 K	from 0.6 GB
28	repeat unslothai · feature-extraction	—	—	unknown	912 K	from 0.5 GB
29	bge-base-zh-v1.5 BAAI · feature-extraction	—	512	✓ mit	812 K	—
30	conv-bert-base YituTech · feature-extraction	—	512	unknown	717 K	—
31	dragon-multiturn-query-encoder nvidia · feature-extraction	—	512	other	713 K	—
32	dragon-multiturn-context-encoder nvidia · feature-extraction	—	512	other	711 K	—
33	Giga-Embeddings-instruct ai-sage · feature-extraction	3.5 B	—	✓ mit	696 K	from 16.2 GB
34	paraphrase-multilingual-MiniLM-L12-v2 Xenova · feature-extraction	120 M	512	unknown	672 K	from 0.8 GB
35	splade-cocondenser-selfdistil naver · feature-extraction	—	512	✗ cc-by-nc-sa-4.0	658 K	—
36	bge-small-en-v1.5 michaelfeil · feature-extraction	30 M	512	✓ mit	599 K	from 0.7 GB
37	Qwen3-VL-Embedding-8B-FP8 RamManavalan · feature-extraction	8.8 B	—	✓ apache-2.0	556 K	from 13.5 GB
38	Qwen3-Embedding-4B-W4A16-G128 boboliu · feature-extraction	4.1 B	41 K	✓ apache-2.0	552 K	from 4.0 GB
39	jina-embeddings-v5-text-nano jinaai · feature-extraction	210 M	8 K	✗ cc-by-nc-4.0	515 K	from 1.1 GB
40	lambda unslothai · feature-extraction	—	—	unknown	499 K	from 0.5 GB
41	hubert-base-ls960 facebook · feature-extraction	—	—	✓ apache-2.0	498 K	—
42	sentence-bert-base-ja-mean-tokens-v2 sonoisa · feature-extraction	110 M	512	cc-by-sa-4.0	474 K	from 1.0 GB
43	pplx-embed-v1-0.6b perplexity-ai · feature-extraction	600 M	33 K	✓ mit	461 K	from 3.2 GB
44	mimi kyutai · feature-extraction	100 M	8 K	✓ cc-by-4.0	458 K	from 0.9 GB
45	MedCPT-Query-Encoder ncbi · feature-extraction	110 M	512	other	454 K	from 1.0 GB
46	bge-small-en-v1.5 Xenova · feature-extraction	30 M	512	unknown	436 K	from 0.6 GB
47	llama-nemotron-embed-1b-v2 nvidia · feature-extraction	1.2 B	131 K	other	429 K	from 3.4 GB

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