AImodelsComparison.com 1,226 open · 200 API
Menu
Models Best of Trending Can I run it? Methodology About
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.

Type
All 1,426 Open weights (self-host) 1,226 API-only 200
Task
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
Runs on
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
Licence
Size
$
48 models
#ModelParamsContextCommercial use30dMin VRAM
01 bge-small-en-v1.5 BAAI · feature-extraction Open weights 30 M 512 ✓ mit 54.0 M from 0.7 GB
02 bge-large-en-v1.5 BAAI · feature-extraction Open weights 340 M 512 ✓ mit 9.7 M from 2.0 GB
03 bge-base-en-v1.5 BAAI · feature-extraction Open weights 110 M 512 ✓ mit 8.6 M from 1.0 GB
04 Qwen3-Embedding-0.6B Qwen · feature-extraction Open weights 600 M 33 K ✓ apache-2.0 8.1 M from 1.9 GB
05 multilingual-e5-large intfloat · feature-extraction Open weights 560 M 512 ✓ mit 6.5 M from 3.0 GB
06 granite-embedding-small-english-r2 ibm-granite · feature-extraction Open weights 50 M 8 K ✓ apache-2.0 5.9 M from 0.6 GB
07 all-MiniLM-L6-v2 Xenova · feature-extraction Open weights 20 M 512 ✓ apache-2.0 4.4 M from 0.5 GB
08 bge-small-zh-v1.5 BAAI · feature-extraction Open weights 20 M 512 ✓ mit 3.5 M from 0.6 GB
09 bge-base-en BAAI · feature-extraction Open weights 110 M 512 ✓ mit 2.4 M from 1.0 GB
10 bge-base-en-v1.5 Xenova · feature-extraction Open weights 110 M 512 ✓ mit 2.3 M from 0.8 GB
11 mxbai-embed-large-v1 mixedbread-ai · feature-extraction Open weights 340 M 512 ✓ apache-2.0 2.0 M from 1.3 GB
12 Qwen3-Embedding-8B Qwen · feature-extraction Open weights 7.6 B 41 K ✓ apache-2.0 2.0 M from 18.3 GB
13 bge-reranker-large BAAI · feature-extraction Open weights 560 M 512 ✓ mit 1.9 M from 3.0 GB
14 Qwen3-Embedding-4B Qwen · feature-extraction Open weights 4.0 B 41 K ✓ apache-2.0 1.8 M from 10.0 GB
15 multilingual-e5-large-instruct intfloat · feature-extraction Open weights 560 M 512 ✓ mit 1.7 M from 1.8 GB
16 jina-embeddings-v3 jinaai · feature-extraction Open weights 570 M 8 K ✗ cc-by-nc-4.0 1.6 M from 1.8 GB
17 SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction Open weights 110 M 512 ✓ apache-2.0 1.4 M from 1.0 GB
18 jina-embeddings-v2-small-en jinaai · feature-extraction Open weights 30 M 8 K ✓ apache-2.0 1.1 M from 0.6 GB
19 w2v-bert-2.0 facebook · feature-extraction Open weights 580 M — ✓ mit 1.1 M from 3.1 GB
20 jina-embeddings-v5-omni-small jinaai · feature-extraction Open weights 1.6 B — ✗ cc-by-nc-4.0 975 K from 4.5 GB
21 UAE-Large-V1 WhereIsAI · feature-extraction Open weights 340 M 512 ✓ mit 952 K from 2.0 GB
22 clap-htsat-unfused laion · feature-extraction Open weights — — ✓ apache-2.0 946 K —
23 1 unslothai · feature-extraction Open weights — 2 K unknown 906 K from 0.5 GB
24 specter2_base allenai · feature-extraction Open weights — 512 ✓ apache-2.0 796 K —
25 repeat unslothai · feature-extraction Open weights — — unknown 765 K from 0.5 GB
26 wavlm-large microsoft · feature-extraction Open weights — — unknown 735 K —
27 bge-small-en-v1.5 Xenova · feature-extraction Open weights 30 M 512 unknown 649 K from 0.6 GB
28 e5-mistral-7b-instruct-bnb-4bit gabor-hosu · feature-extraction Open weights 7.3 B 33 K ✓ mit 605 K from 5.8 GB
29 bge-small-en-v1.5 michaelfeil · feature-extraction Open weights 30 M 512 ✓ mit 599 K from 0.7 GB
30 KURE-v1 nlpai-lab · feature-extraction Open weights 568 M 8 K ✓ mit 578 K from 3.1 GB
31 wavlm-base-plus microsoft · feature-extraction Open weights — — unknown 550 K —
32 FRIDA ai-forever · feature-extraction Open weights 823 M — ✓ mit 524 K from 4.2 GB
33 jina-embeddings-v5-text-nano jinaai · feature-extraction Open weights 210 M 8 K ✗ cc-by-nc-4.0 515 K from 1.1 GB
34 hubert-base-ls960 facebook · feature-extraction Open weights — — ✓ apache-2.0 496 K —
35 multilingual-e5-small Xenova · feature-extraction Open weights 120 M 512 unknown 477 K from 0.8 GB
36 conv-bert-base YituTech · feature-extraction Open weights — 512 unknown 475 K —
37 sentence-bert-base-ja-mean-tokens-v2 sonoisa · feature-extraction Open weights 110 M 512 cc-by-sa-4.0 474 K from 1.0 GB
38 pplx-embed-v1-0.6b perplexity-ai · feature-extraction Open weights 600 M 33 K ✓ mit 461 K from 3.2 GB
39 mimi kyutai · feature-extraction Open weights 100 M 8 K ✓ cc-by-4.0 458 K from 0.9 GB
40 MedCPT-Query-Encoder ncbi · feature-extraction Open weights 110 M 512 other 454 K from 1.0 GB
41 splade-cocondenser-selfdistil naver · feature-extraction Open weights — 512 ✗ cc-by-nc-sa-4.0 452 K —
42 dragon-multiturn-query-encoder nvidia · feature-extraction Open weights — 512 other 448 K —
43 dragon-multiturn-context-encoder nvidia · feature-extraction Open weights — 512 other 448 K —
44 larger_clap_music_and_speech laion · feature-extraction Open weights — — ✓ apache-2.0 447 K —
45 indobert-base-p1 indobenchmark · feature-extraction Open weights — 512 ✓ mit 437 K —
46 lambda unslothai · feature-extraction Open weights — — unknown 430 K from 0.5 GB
47 vram-16 unslothai · feature-extraction Open weights — — unknown 390 K from 0.5 GB
48 larger_clap_general laion · feature-extraction Open weights — — ✓ apache-2.0 346 K —
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.