Small Model Hub

3,618 efficient AI models across 9 domains · Charts · API

Domain

All (3,618)Vision (1,615)3D (743)Embedding (472)Multimodal (305)Edge/Mobile (172)Code (125)Speech (89)Video (49)NLP (48)

Max Size≤10M ≤50M ≤100M ≤500M All

Max VRAM≤512MB ≤1GB ≤2GB ≤4GB ≤8GB All

Score

Raw Context (0-100)

Percentile rank within each task — comparable across domains

Showing 135 models

#	Model	Domain	Task	Params ↑	GFLOPs	VRAM	Context	Speed	Arch	Source
1	NeuML/pubmedbert-base-embeddings-1M	Embedding	Text Embedding	1.00M	—	2 MB	—	—	dense	MTEB
2	NeuML/pubmedbert-base-embeddings-500K	Embedding	Text Embedding	1.00M	—	2 MB	—	—	dense	MTEB
3	axiotic/ogma-micro	Embedding	Text Embedding	2.00M	—	9 MB	—	—	dense	MTEB
4	minishlab/potion-base-2M	Embedding	Text Embedding	2.00M	—	7 MB	—	—	dense	MTEB
5	NeuML/pubmedbert-base-embeddings-2M	Embedding	Text Embedding	2.00M	—	7 MB	—	—	dense	MTEB
6	axiotic/ogma-mini	Embedding	Text Embedding	4.00M	—	13 MB	—	—	dense	MTEB
7	minishlab/potion-base-4M	Embedding	Text Embedding	4.00M	—	14 MB	—	—	dense	MTEB
8	cross-encoder/ms-marco-TinyBERT-L2-v2	Embedding	Text Embedding	4.00M	—	17 MB	—	—	cross-encoder	MTEB
9	google/yamnet	Embedding	Text Embedding	4.00M	—	14 MB	—	—	dense	MTEB
10	minishlab/M2V_base_output	Embedding	Text Embedding	8.00M	—	29 MB	—	—	dense	MTEB
11	minishlab/potion-base-8M	Embedding	Text Embedding	8.00M	—	29 MB	—	—	dense	MTEB
12	NeuML/pubmedbert-base-embeddings-8M	Embedding	Text Embedding	8.00M	—	30 MB	—	—	dense	MTEB
13	axiotic/ogma-small	Embedding	Text Embedding	9.00M	—	33 MB	—	—	dense	MTEB
14	marksverdhei/Qwen3-Voice-Embedding-12Hz-0.6B	Embedding	Text Embedding	9.00M	—	17 MB	—	—	dense	MTEB
15	shekar-ai/Noql	Embedding	Text Embedding	12.0M	—	46 MB	—	—	dense	MTEB
16	marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B	Embedding	Text Embedding	12.0M	—	23 MB	—	—	dense	MTEB
17	cointegrated/rubert-tiny	Embedding	Text Embedding	12.0M	—	45 MB	—	—	dense	MTEB
18	axiotic/ogma-base	Embedding	Text Embedding	13.0M	—	51 MB	—	—	dense	MTEB
19	Mihaiii/Squirtle	Embedding	Text Embedding	16.0M	—	60 MB	—	—	dense	MTEB
20	Mihaiii/Venusaur	Embedding	Text Embedding	16.0M	—	60 MB	—	—	dense	MTEB
21	minishlab/potion-code-16M-v2	Embedding	Text Embedding	16.0M	—	62 MB	—	—	dense	MTEB
22	cross-encoder/ms-marco-MiniLM-L2-v2	Embedding	Text Embedding	16.0M	—	60 MB	—	—	cross-encoder	MTEB
23	RikkaBotan/quantized-stable-static-embedding-fast-retrieval-mrl-en	Embedding	Text Embedding	16.0M	—	8 MB	—	—	dense	MTEB
24	RikkaBotan/stable-static-embedding-fast-retrieval-mrl-en	Embedding	Text Embedding	16.0M	—	60 MB	—	—	dense	MTEB
25	RikkaBotan/stable-static-embedding-fast-retrieval-mrl-en-v2	Embedding	Text Embedding	16.0M	—	60 MB	—	—	dense	MTEB
26	cross-encoder/ettin-reranker-17m-v1	Embedding	Text Embedding	17.0M	—	64 MB	—	—	cross-encoder	MTEB
27	Mihaiii/Bulbasaur	Embedding	Text Embedding	17.0M	—	66 MB	—	—	dense	MTEB
28	Mihaiii/Wartortle	Embedding	Text Embedding	17.0M	—	66 MB	—	—	dense	MTEB
29	Mihaiii/gte-micro	Embedding	Text Embedding	17.0M	—	66 MB	—	—	dense	MTEB
30	mixedbread-ai/mxbai-edge-colbert-v0-17m	Embedding	Text Embedding	17.0M	—	64 MB	—	—	late-interaction	MTEB
31	lightonai/LateOn-Code-edge	Embedding	Text Embedding	17.0M	—	64 MB	—	—	late-interaction	MTEB
32	lightonai/LateOn-Code-edge-pretrain	Embedding	Text Embedding	17.0M	—	64 MB	—	—	late-interaction	MTEB
33	RikkaBotan/quantized-stable-static-embedding-fast-retrieval-mrl-ja	Embedding	Text Embedding	17.0M	—	9 MB	—	—	dense	MTEB
34	RikkaBotan/stable-static-embedding-fast-retrieval-mrl-ja	Embedding	Text Embedding	17.0M	—	64 MB	—	—	dense	MTEB
35	Mihaiii/gte-micro-v4	Embedding	Text Embedding	19.0M	—	73 MB	—	—	dense	MTEB
36	cross-encoder/ms-marco-MiniLM-L4-v2	Embedding	Text Embedding	19.0M	—	73 MB	—	—	cross-encoder	MTEB
37	asapp/sew-d-tiny-100k-ft-ls100h	Embedding	Text Embedding	20.0M	—	92 MB	—	—	dense	MTEB
38	facebook/dinov2-small	Embedding	Text Embedding	22.0M	—	84 MB	—	—	dense	MTEB
39	facebook/dinov3-vits16-pretrain-lvd1689m	Embedding	Text Embedding	22.0M	—	82 MB	—	—	dense	MTEB
40	matthewagi/HeAR-s1.1	Embedding	Text Embedding	22.0M	—	84 MB	—	—	dense	MTEB
41	Snowflake/snowflake-arctic-embed-xs	Embedding	Text Embedding	23.0M	—	86 MB	—	—	dense	MTEB
42	facebook/encodec_24khz	Embedding	Text Embedding	23.0M	—	88 MB	—	—	dense	MTEB
43	geoffsee/auto-g-embed-st	Embedding	Text Embedding	23.0M	—	87 MB	—	—	dense	MTEB
44	MongoDB/mdbr-leaf-ir	Embedding	Text Embedding	23.0M	—	86 MB	—	—	dense	MTEB
45	MongoDB/mdbr-leaf-mt	Embedding	Text Embedding	23.0M	—	86 MB	—	—	dense	MTEB
46	Mihaiii/Ivysaur	Embedding	Text Embedding	23.0M	—	87 MB	—	—	dense	MTEB
47	avsolatorio/GIST-all-MiniLM-L6-v2	Embedding	Text Embedding	23.0M	—	87 MB	—	—	dense	MTEB
48	brahmairesearch/slx-v0.1	Embedding	Text Embedding	23.0M	—	87 MB	—	—	dense	MTEB
49	opensearch-project/opensearch-neural-sparse-encoding-doc-v2-mini	Embedding	Text Embedding	23.0M	—	86 MB	—	—	sparse	MTEB
50	rasgaard/m2v-dfm-large	Embedding	Text Embedding	23.0M	—	87 MB	—	—	dense	MTEB
51	cross-encoder/ms-marco-MiniLM-L6-v2	Embedding	Text Embedding	23.0M	—	87 MB	—	—	cross-encoder	MTEB
52	sentence-transformers/all-MiniLM-L6-v2	Embedding	Text Embedding	23.0M	—	87 MB	—	—	dense	MTEB
53	sentence-transformers/multi-qa-MiniLM-L6-cos-v1	Embedding	Text Embedding	23.0M	—	87 MB	—	—	dense	MTEB
54	mixedbread-ai/mxbai-embed-xsmall-v1	Embedding	Text Embedding	24.0M	—	58 MB	—	—	dense	MTEB
55	moka-ai/m3e-small	Embedding	Text Embedding	24.0M	—	58 MB	—	—	dense	MTEB
56	facebook/dinov3-vits16plus-pretrain-lvd1689m	Embedding	Text Embedding	29.0M	—	109 MB	—	—	dense	MTEB
57	cointegrated/rubert-tiny2	Embedding	Text Embedding	29.0M	—	112 MB	—	—	dense	MTEB
58	sergeyzh/rubert-tiny-turbo	Embedding	Text Embedding	29.0M	—	111 MB	—	—	dense	MTEB
59	thenlper/gte-small-zh	Embedding	Text Embedding	30.0M	—	58 MB	—	—	dense	MTEB
60	ibm-granite/granite-embedding-30m-english	Embedding	Text Embedding	30.0M	—	58 MB	—	—	dense	MTEB
61	erikkaum/lattice-retrieval	Embedding	Text Embedding	31.0M	—	119 MB	—	—	dense	MTEB
62	sentence-transformers/static-retrieval-mrl-en-v1	Embedding	Text Embedding	31.0M	—	119 MB	—	—	dense	MTEB
63	cross-encoder/ettin-reranker-32m-v1	Embedding	Text Embedding	32.0M	—	122 MB	—	—	cross-encoder	MTEB
64	mixedbread-ai/mxbai-edge-colbert-v0-32m	Embedding	Text Embedding	32.0M	—	122 MB	—	—	late-interaction	MTEB
65	minishlab/potion-base-32M	Embedding	Text Embedding	32.0M	—	123 MB	—	—	dense	MTEB
66	minishlab/potion-retrieval-32M	Embedding	Text Embedding	32.0M	—	123 MB	—	—	dense	MTEB
67	sergeyzh/rubert-mini-frida	Embedding	Text Embedding	32.0M	—	123 MB	—	—	dense	MTEB
68	Snowflake/snowflake-arctic-embed-s	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
69	BAAI/bge-small-en	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
70	BAAI/bge-small-en-v1.5	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
71	BAAI/bge-small-zh	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
72	BAAI/bge-small-zh-v1.5	Embedding	Text Embedding	33.0M	—	91 MB	—	—	dense	MTEB
73	thu-nmrc/bge-small-structural-separator	Embedding	Text Embedding	33.0M	—	79 MB	—	—	dense	MTEB
74	intfloat/e5-small	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
75	intfloat/e5-small-v2	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
76	jinaai/jina-embeddings-v2-small-en	Embedding	Text Embedding	33.0M	—	62 MB	—	—	dense	MTEB
77	ManiacLabs/miniac-embed	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
78	abhinand/MedEmbed-small-v0.1	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
79	avsolatorio/GIST-small-Embedding-v0	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
80	avsolatorio/NoInstruct-small-Embedding-v0	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
81	thenlper/gte-small	Embedding	Text Embedding	33.0M	—	64 MB	—	—	dense	MTEB
82	cross-encoder/ms-marco-MiniLM-L12-v2	Embedding	Text Embedding	33.0M	—	127 MB	—	—	cross-encoder	MTEB
83	sentence-transformers/all-MiniLM-L12-v2	Embedding	Text Embedding	33.0M	—	127 MB	—	—	dense	MTEB
84	deepvk/USER2-small	Embedding	Text Embedding	34.0M	—	131 MB	—	—	dense	MTEB
85	jinaai/jina-embedding-s-en-v1	Embedding	Text Embedding	35.0M	—	134 MB	—	—	dense	MTEB
86	cl-nagoya/ruri-v3-30m	Embedding	Text Embedding	37.0M	—	140 MB	—	—	dense	MTEB
87	exp-models/dragonkue-KoEn-E5-Tiny	Embedding	Text Embedding	38.0M	—	143 MB	—	—	dense	MTEB
88	openai/whisper-tiny	Embedding	Text Embedding	39.0M	—	144 MB	—	—	dense	MTEB
89	clips/e5-small-trm-nl	Embedding	Text Embedding	41.0M	—	78 MB	—	—	dense	MTEB
90	andersborges/model2vecdk	Embedding	Text Embedding	48.0M	—	183 MB	—	—	dense	MTEB
91	ibm-granite/granite-embedding-small-english-r2	Embedding	Text Embedding	48.0M	—	91 MB	—	—	dense	MTEB
92	andersborges/model2vecdk-stem	Embedding	Text Embedding	49.0M	—	185 MB	—	—	dense	MTEB
93	RikkaBotan/quantized-stable-static-embedding-fast-retrieval-mrl-bilingual-ja-en	Embedding	Text Embedding	50.0M	—	25 MB	—	—	dense	MTEB
94	RikkaBotan/stable-static-embedding-fast-retrieval-mrl-bilingual-ja-en	Embedding	Text Embedding	50.0M	—	189 MB	—	—	dense	MTEB
95	BorisTM/starse	Embedding	Text Embedding	62.0M	—	8 MB	—	—	dense	MTEB
96	opensearch-project/opensearch-neural-sparse-encoding-doc-v2-distill	Embedding	Text Embedding	66.0M	—	267 MB	—	—	sparse	MTEB
97	opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill	Embedding	Text Embedding	66.0M	—	267 MB	—	—	sparse	MTEB
98	prdev/mini-gte	Embedding	Text Embedding	66.0M	—	253 MB	—	—	dense	MTEB
99	cross-encoder/ettin-reranker-68m-v1	Embedding	Text Embedding	68.0M	—	260 MB	—	—	cross-encoder	MTEB
100	dmedhi/PawanEmbd-68M	Embedding	Text Embedding	68.0M	—	260 MB	—	—	dense	MTEB
101	cl-nagoya/ruri-small	Embedding	Text Embedding	68.0M	—	130 MB	—	—	dense	MTEB
102	cl-nagoya/ruri-small-v2	Embedding	Text Embedding	68.0M	—	260 MB	—	—	dense	MTEB
103	amgix/static-retrieval-multilingual-69m-v1	Embedding	Text Embedding	69.0M	—	274 MB	—	—	dense	MTEB
104	nanovdr/NanoVDR-S-Multi	Embedding	Text Embedding	69.0M	—	282 MB	—	—	dense	MTEB
105	cl-nagoya/ruri-v3-70m	Embedding	Text Embedding	70.0M	—	140 MB	—	—	dense	MTEB
106	mixedbread-ai/mxbai-rerank-xsmall-v1	Embedding	Text Embedding	71.0M	—	135 MB	—	—	cross-encoder	MTEB
107	google/vggish	Embedding	Text Embedding	72.0M	—	275 MB	—	—	dense	MTEB
108	DMetaSoul/Dmeta-embedding-zh-small	Embedding	Text Embedding	74.0M	—	283 MB	—	—	dense	MTEB
109	openai/whisper-base	Embedding	Text Embedding	74.0M	—	277 MB	—	—	dense	MTEB
110	codefuse-ai/F2LLM-v2-80M	Embedding	Text Embedding	80.0M	—	305 MB	—	—	dense	MTEB
111	speechbrain/cnn14-esc50	Embedding	Text Embedding	81.0M	—	308 MB	—	—	dense	MTEB
112	mispeech/dasheng-base	Embedding	Text Embedding	85.0M	—	326 MB	—	—	dense	MTEB
113	facebook/dinov3-vitb16-pretrain-lvd1689m	Embedding	Text Embedding	86.0M	—	327 MB	—	—	dense	MTEB
114	MCG-NJU/videomae-base	Embedding	Text Embedding	86.0M	—	329 MB	—	—	dense	MTEB
115	MCG-NJU/videomae-base-finetuned-kinetics	Embedding	Text Embedding	86.0M	—	329 MB	—	—	dense	MTEB
116	MIT/ast-finetuned-audioset-10-10-0.4593	Embedding	Text Embedding	87.0M	—	330 MB	—	—	dense	MTEB
117	facebook/dinov2-base	Embedding	Text Embedding	87.0M	—	330 MB	—	—	dense	MTEB
118	nyu-visionx/moco-v3-vit-b	Embedding	Text Embedding	87.0M	—	330 MB	—	—	dense	MTEB
119	facebook/data2vec-audio-base-960h	Embedding	Text Embedding	93.0M	—	355 MB	—	—	dense	MTEB
120	nomic-ai/nomic-embed-vision-v1.5	Embedding	Text Embedding	93.0M	—	355 MB	—	—	dense	MTEB
121	microsoft/unispeech-sat-base-100h-libri-ft	Embedding	Text Embedding	94.0M	—	359 MB	—	—	dense	MTEB
122	facebook/hubert-base-ls960	Embedding	Text Embedding	95.0M	—	360 MB	—	—	dense	MTEB
123	asapp/sew-d-base-plus-400k-ft-ls100h	Embedding	Text Embedding	95.0M	—	675 MB	—	—	dense	MTEB
124	facebook/wav2vec2-base	Embedding	Text Embedding	95.0M	—	362 MB	—	—	dense	MTEB
125	facebook/wav2vec2-base-960h	Embedding	Text Embedding	95.0M	—	360 MB	—	—	dense	MTEB
126	microsoft/wavlm-base	Embedding	Text Embedding	95.0M	—	361 MB	—	—	dense	MTEB
127	microsoft/wavlm-base-plus	Embedding	Text Embedding	95.0M	—	361 MB	—	—	dense	MTEB
128	microsoft/wavlm-base-plus-sd	Embedding	Text Embedding	95.0M	—	361 MB	—	—	dense	MTEB
129	microsoft/wavlm-base-plus-sv	Embedding	Text Embedding	95.0M	—	361 MB	—	—	dense	MTEB
130	microsoft/wavlm-base-sd	Embedding	Text Embedding	95.0M	—	361 MB	—	—	dense	MTEB
131	microsoft/wavlm-base-sv	Embedding	Text Embedding	95.0M	—	361 MB	—	—	dense	MTEB
132	ibm-granite/granite-embedding-97m-multilingual-r2	Embedding	Text Embedding	97.0M	—	186 MB	—	—	dense	MTEB
133	Quazim0t0/Byrne-Embed	Embedding	Text Embedding	98.0M	—	327 MB	—	—	dense	MTEB
134	nvidia/RADIO-B	Embedding	Text Embedding	98.0M	—	375 MB	—	—	dense	MTEB
135	malenia1/ternary-weight-embedding	Embedding	Text Embedding	99.0M	—	158 MB	—	—	dense	MTEB