Discover the Best AI Models

Search, analyze, and download from our global directory of 3,000+ open-source models.

Model Index 55939 Total

sentence-transformers

sentence-transformers/all-MiniLM-L6-v2

No description available.

🔗 sentence-similarity 197,060,768
google-bert

google-bert/bert-base-uncased

BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the ...

🎭 fill-mask 65,190,605
google

google/electra-base-discriminator

No description available.

✨ General AI Model 48,477,307
Falconsai

Falconsai/nsfw_image_detection

The Fine-Tuned Vision Transformer (ViT) is a variant of the transformer encoder architecture, similar to BERT, that has been adapted for ima...

📸 image-classification 41,133,499
sentence-transformers

sentence-transformers/all-mpnet-base-v2

No description available.

🔗 sentence-similarity 27,427,849
timm

timm/mobilenetv3_small_100.lamb_in1k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 2.5 - GMACs: 0.1 - Activations (M): 1.4 - Image size: 224 x...

📸 image-classification 24,518,893
FacebookAI

FacebookAI/roberta-large

RoBERTa is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on t...

🎭 fill-mask 22,418,408
sentence-transformers

sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

No description available.

🔗 sentence-similarity 22,244,504
Qwen

Qwen/Qwen2.5-7B-Instruct

No description available.

📝 text-generation 20,825,802
laion

laion/clap-htsat-fused

No description available.

🎧 audio-classification 20,352,951
openai

openai/clip-vit-base-patch32

The CLIP model was developed by researchers at OpenAI to learn about what contributes to robustness in computer vision tasks. The model was ...

🎯 zero-shot-image-classification 20,032,440
FacebookAI

FacebookAI/xlm-roberta-base

XLM-RoBERTa is a multilingual version of RoBERTa. It is pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. RoBERTa ...

🎭 fill-mask 19,256,753
BAAI

BAAI/bge-m3

No description available.

🔗 sentence-similarity 18,424,358
amazon

amazon/chronos-2

- time series - forecasting - foundation models - pretrained models - safetensors - https://arxiv.org/abs/2510.15821 - autogluon/chronosdata...

🕒 time-series-forecasting 17,962,090
Bingsu

Bingsu/adetailer

No description available.

✨ General AI Model 17,007,348
pyannote

pyannote/wespeaker-voxceleb-resnet34-LM

No description available.

✨ General AI Model 15,761,561
pyannote

pyannote/segmentation-3.0

No description available.

🔊 voice-activity-detection 15,498,976
pyannote

pyannote/speaker-diarization-3.1

No description available.

🎙️ automatic-speech-recognition 13,708,933
cross-encoder

cross-encoder/ms-marco-MiniLM-L6-v2

No description available.

🏆 text-ranking 13,698,362
Qwen

Qwen/Qwen3-VL-2B-Instruct

No description available.

📖 image-text-to-text 13,328,669
alana89

alana89/TabSTAR

No description available.

📑 tabular-classification 13,261,848
colbert-ir

colbert-ir/colbertv2.0

No description available.

✨ General AI Model 13,101,998
Xenova

Xenova/paraphrase-multilingual-MiniLM-L12-v2

No description available.

🔍 feature-extraction 12,225,956
Qwen

Qwen/Qwen3-0.6B

Qwen3-0.6B has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: ...

📝 text-generation 11,578,352
omni-research

omni-research/Tarsier2-Recap-7b

Base Model: Qwen2-VL-7B-Instruct - Training Data: Tarsier2-Recap-585K Model date: Tarsier2-Recap-7b was trained in December 2024. Paper or r...

✨ General AI Model 11,117,272
FacebookAI

FacebookAI/roberta-base

RoBERTa is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on t...

🎭 fill-mask 10,346,496
openai-community

openai-community/gpt2

GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained o...

📝 text-generation 10,210,526
Comfy-Org

Comfy-Org/Wan_2.2_ComfyUI_Repackaged

No description available.

✨ General AI Model 9,858,893
hexgrad

hexgrad/Kokoro-82M

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to large...

🗣️ text-to-speech 9,828,072
Kijai

Kijai/WanVideo_comfy

Combined and quantized models for WanVideo, originating from here:...

✨ General AI Model 9,439,669
autogluon

autogluon/chronos-bolt-small

No description available.

🕒 time-series-forecasting 9,395,788
distilbert

distilbert/distilbert-base-uncased

DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, usin...

🎭 fill-mask 8,121,555
coqui

coqui/XTTS-v2

No description available.

🗣️ text-to-speech 8,081,180
Qwen

Qwen/Qwen3-VL-8B-Instruct

No description available.

📖 image-text-to-text 8,019,083
facebook

facebook/contriever

This model has been trained without supervision following the approach described in Towards Unsupervised Dense Information Retrieval with Co...

✨ General AI Model 7,512,479
Qwen

Qwen/Qwen2.5-1.5B-Instruct

No description available.

📝 text-generation 7,235,449
openai

openai/gpt-oss-20b

No description available.

📝 text-generation 7,221,396
dima806

dima806/fairface_age_image_detection

Detects age group with about 59% accuracy based on an image....

📸 image-classification 7,175,244
meta-llama

meta-llama/Llama-3.1-8B-Instruct

- en - de - fr - it - pt - hi - es - th basemodel: meta-llama/Meta-Llama-3.1-8B pipelinetag: text-generation - facebook - meta - pytorch - l...

📝 text-generation 7,163,568
apple

apple/DFN5B-CLIP-ViT-H-14-378

Model Type: Contrastive Image-Text, Zero-Shot Image Classification. - Dataset: DFN-5b - Papers: - Data Filtering Networks: https://arxiv.org...

✨ General AI Model 7,085,733
Qwen

Qwen/Qwen2.5-0.5B-Instruct

No description available.

📝 text-generation 6,964,401
timm

timm/convnextv2_nano.fcmae_ft_in22k_in1k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 15.6 - GMACs: 2.5 - Activations (M): 8.4 - Image size: trai...

📸 image-classification 6,931,035
openai

openai/clip-vit-large-patch14

The CLIP model was developed by researchers at OpenAI to learn about what contributes to robustness in computer vision tasks. The model was ...

🎯 zero-shot-image-classification 6,880,423
Qwen

Qwen/Qwen2.5-3B-Instruct

No description available.

📝 text-generation 6,652,654
Qwen

Qwen/Qwen3-1.7B

Qwen3-1.7B has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: ...

📝 text-generation 6,438,824
BAAI

BAAI/bge-small-en-v1.5

- sentence-transformers - feature-extraction - sentence-similarity - transformers - mteb - name: bge-small-en-v1.5 results: - task: type: Cl...

🔍 feature-extraction 6,418,718
FacebookAI

FacebookAI/xlm-roberta-large

XLM-RoBERTa is a multilingual version of RoBERTa. It is pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. RoBERTa ...

🎭 fill-mask 6,411,244
Qwen

Qwen/Qwen3-8B

Qwen3-8B has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 8....

📝 text-generation 6,387,534
sentence-transformers

sentence-transformers/paraphrase-multilingual-mpnet-base-v2

No description available.

🔗 sentence-similarity 6,263,512
trl-internal-testing

trl-internal-testing/tiny-Qwen2ForCausalLM-2.5

No description available.

📝 text-generation 6,139,720
1 2 3