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
$
1,226 models
#ModelParamsContextCommercial use30dMin VRAM
01 all-MiniLM-L6-v2 sentence-transformers · sentence-similarity Open weights 20 M 512 ✓ apache-2.0 193.4 M from 0.6 GB
02 bge-small-en-v1.5 BAAI · feature-extraction Open weights 30 M 512 ✓ mit 54.0 M from 0.7 GB
03 paraphrase-multilingual-MiniLM-L12-v2 sentence-transformers · sentence-similarity Open weights 120 M 512 ✓ apache-2.0 40.6 M from 1.0 GB
04 bge-m3 BAAI · sentence-similarity Open weights — 8 K ✓ mit 29.6 M —
05 Qwen3-0.6B Qwen · text-generation Open weights 750 M 41 K ✓ apache-2.0 25.2 M from 2.3 GB
06 t5-small google-t5 · translation Open weights 60 M — ✓ apache-2.0 23.9 M from 0.8 GB
07 gpt2 openai-community · text-generation Open weights 140 M — ✓ mit 18.8 M from 1.1 GB
08 all-mpnet-base-v2 sentence-transformers · sentence-similarity Open weights 110 M 512 ✓ apache-2.0 17.9 M from 1.0 GB
09 mobilenetv3_small_100.lamb_in1k timm · image-classification Open weights <0.1 M — ✓ apache-2.0 17.0 M from 0.5 GB
10 wav2vec2-large-xlsr-53-japanese jonatasgrosman · ASR Open weights — — ✓ apache-2.0 15.8 M —
11 bge-reranker-v2-m3 BAAI · text-classification Open weights 570 M 8 K ✓ apache-2.0 14.7 M from 3.1 GB
12 vit-base-patch16-224 google · image-classification Open weights 90 M — ✓ apache-2.0 14.0 M from 0.9 GB
13 nomic-embed-text-v1.5 nomic-ai · sentence-similarity Open weights 140 M 2 K ✓ apache-2.0 12.4 M from 1.1 GB
14 whisperkit-coreml argmaxinc · ASR Open weights — — ✓ mit 11.5 M —
15 Qwen3-4B Qwen · text-generation Open weights 4.0 B 41 K ✓ apache-2.0 11.4 M from 10.0 GB
16 Kokoro-82M hexgrad · text-to-speech Open weights 82 M — ✓ apache-2.0 10.1 M from 0.7 GB
17 bge-large-en-v1.5 BAAI · feature-extraction Open weights 340 M 512 ✓ mit 9.7 M from 2.0 GB
18 Qwen3-14B Qwen · text-generation Open weights Also via API 14.8 B 41 K ✓ apache-2.0 9.4 M from 35.2 GB
19 multilingual-e5-small intfloat · sentence-similarity Open weights 120 M 512 ✓ mit 9.2 M from 1.0 GB
20 gemma-4-26B-A4B-it google · image-text-to-text Open weights Also via API 26.5 B — ✓ apache-2.0 9.1 M from 61.3 GB
21 bge-base-en-v1.5 BAAI · feature-extraction Open weights 110 M 512 ✓ mit 8.6 M from 1.0 GB
22 paraphrase-multilingual-mpnet-base-v2 sentence-transformers · sentence-similarity Open weights 280 M 512 ✓ apache-2.0 8.6 M from 1.8 GB
23 gemma-4-31B-it google · image-text-to-text Open weights Also via API 32.7 B — ✓ apache-2.0 8.5 M from 74.2 GB
24 locate-anything.cpp-gguf mudler · object-detection Open weights 3.8 B — other 8.3 M from 6.3 GB
25 Qwen3-Embedding-0.6B Qwen · feature-extraction Open weights 600 M 33 K ✓ apache-2.0 8.1 M from 1.9 GB
26 Qwen3-8B Qwen · text-generation Open weights 8.2 B 41 K ✓ apache-2.0 8.1 M from 19.7 GB
27 Qwen3.8-27B Qwen · image-text-to-text Open weights Also via API 27.8 B — ✓ apache-2.0 7.7 M from 65.8 GB
28 Qwen3.5-4B Qwen · image-text-to-text Open weights 4.7 B — ✓ apache-2.0 7.5 M from 11.5 GB
29 clap-htsat-fused laion · audio-classification Open weights 150 M — ✓ apache-2.0 7.2 M from 1.2 GB
30 speaker-diarization-3.1 pyannote · ASR · gated Open weights — — ✓ mit 6.7 M —
31 audio.cpp-gguf audio-cpp · text-to-speech Open weights — — other 6.6 M from 1.6 GB
32 Qwen3.8-Flash-Next-GSQ-RCO-GGUF ISTA-DASLab · image-text-to-text Open weights 180.0 B — ✓ apache-2.0 6.5 M from 28.5 GB
33 multilingual-e5-large intfloat · feature-extraction Open weights 560 M 512 ✓ mit 6.5 M from 3.0 GB
34 Qwen2.5-7B-Instruct Qwen · text-generation Open weights Also via API 7.6 B 33 K ✓ apache-2.0 6.4 M from 18.4 GB
35 Qwen3.5-9B Qwen · image-text-to-text Open weights Also via API 9.7 B — ✓ apache-2.0 6.4 M from 23.2 GB
36 GLM-5.3-Flash zai-org · image-text-to-text Open weights Also via API 321.3 B — ✓ mit 6.3 M from 409.9 GB
37 XTTS-v2 coqui · text-to-speech Open weights — — other 6.1 M —
38 Gender-Classifier-Mini prithivMLmods · image-classification Open weights 93 M — ✓ apache-2.0 6.1 M from 1.7 GB
39 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
40 whisper-large-v3-turbo openai · ASR Open weights 810 M — ✓ mit 5.8 M from 2.4 GB
41 gpt-oss-20b openai · text-generation Open weights Also via API 21.5 B 131 K ✓ apache-2.0 5.7 M from 34.0 GB
42 multilingual-e5-base intfloat · sentence-similarity Open weights 280 M 512 ✓ mit 5.6 M from 1.8 GB
43 opt-125m facebook · text-generation Open weights 125 M 2 K other 5.6 M from 0.8 GB
44 DeepSeek-V3.2 deepseek-ai · text-generation Open weights Also via API 685.4 B 164 K ✓ mit 5.4 M from 861.7 GB
45 Qwen2.5-0.5B-Instruct Qwen · text-generation Open weights 490 M 33 K ✓ apache-2.0 5.3 M from 1.7 GB
46 Ornith-1.5-9B-GGUF ornith-ai · text-generation Open weights — — ✓ mit 5.0 M from 6.9 GB
47 speaker-diarization-community-1 pyannote · ASR · gated Open weights — — ✓ cc-by-4.0 5.0 M —
48 Qwen2.5-VL-7B-Instruct Qwen · image-text-to-text Open weights 8.3 B 128 K ✓ apache-2.0 4.9 M from 20.0 GB
49 Ornith-1.0-9B-GGUF deepreinforce-ai · text-generation Open weights — — ✓ mit 4.9 M from 6.7 GB
50 Llama-3.1-8B-Instruct meta-llama · text-generation · gated Open weights Also via API 8.0 B — ⚠ llama3.1 4.9 M from 19.4 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.