Discover the Best AI Models

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

Model Index 55939 Total

segment-any-text

segment-any-text/sat-3l-sm

No description available.

🏷️ token-classification 222,365
lmstudio-community

lmstudio-community/LFM2-24B-A2B-MLX-5bit

No description available.

📝 text-generation 222,299
MoritzLaurer

MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7

This multilingual model can perform natural language inference (NLI) on 100 languages and is therefore also suitable for multilingual zero-s...

🎯 zero-shot-classification 222,252
ai-forever

ai-forever/FRIDA

- name: FRIDA results: - dataset: config: default name: MTEB CEDRClassification (default) revision: c0ba03d058e3e1b2f3fd20518875a4563dd12db4...

🔍 feature-extraction 222,223
zhihan1996

zhihan1996/DNABERT-2-117M

This is the official pre-trained model introduced in DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome ....

✨ General AI Model 222,146
BAAI

BAAI/bge-large-en

- mteb - sentence-transfomres - transformers - name: bge-large-en results: - task: type: Classification dataset: type: mteb/amazoncounterfac...

🔍 feature-extraction 222,008
rizvandwiki

rizvandwiki/gender-classification-2

- image-classification - pytorch - huggingpics - accuracy...

📸 image-classification 221,856
superb

superb/wav2vec2-base-superb-er

This is a ported version of S3PRL's Wav2Vec2 for the SUPERB Emotion Recognition task. The base model is wav2vec2-base, which is pretrained o...

🎧 audio-classification 221,649
timm

timm/tf_efficientnet_b0.ns_jft_in1k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 5.3 - GMACs: 0.4 - Activations (M): 6.7 - Image size: 224 x...

📸 image-classification 221,551
BAAI

BAAI/bge-small-en

- mteb - sentence transformers - name: bge-small-en results: - task: type: Classification dataset: type: mteb/amazoncounterfactual name: MTE...

🔍 feature-extraction 221,521
Snowflake

Snowflake/snowflake-arctic-embed-s

pipelinetag: sentence-similarity - sentence-transformers - feature-extraction - sentence-similarity - mteb - arctic - snowflake-arctic-embed...

🔗 sentence-similarity 221,345
microsoft

microsoft/VibeVoice-1.5B

No description available.

🗣️ text-to-speech 221,155
facebook

facebook/nougat-base

Nougat is a Donut model trained to transcribe scientific PDFs into an easy-to-use markdown format. The model consists of a Swin Transformer ...

🖼️ image-to-text 220,358
cyankiwi

cyankiwi/GLM-4.7-Flash-AWQ-4bit

No description available.

📝 text-generation 220,344
abhishekchohan

abhishekchohan/gemma-3-12b-it-quantized-W4A16

No description available.

📖 image-text-to-text 220,205
EleutherAI

EleutherAI/enformer-official-rough

Enformer is a neural network architecture based on the Transformer that led to greatly increased accuracy in predicting gene expression from...

✨ General AI Model 219,482
Qwen

Qwen/Qwen2.5-3B-Instruct-GGUF

No description available.

📝 text-generation 217,983
facebook

facebook/sam2.1-hiera-large

No description available.

🎭 mask-generation 217,756
answerdotai

answerdotai/ModernBERT-large

No description available.

🎭 fill-mask 217,358
Qwen

Qwen/Qwen3.5-27B-FP8

Type: Causal Language Model with Vision Encoder - Training Stage: Pre-training & Post-training - Language Model - Number of Parameters: 27B ...

📖 image-text-to-text 216,491
dslim

dslim/bert-large-NER

bert-large-NER is a fine-tuned BERT model that is ready to use for Named Entity Recognition and achieves state-of-the-art performance for th...

🏷️ token-classification 215,504
nvidia

nvidia/NVIDIA-Nemotron-Nano-9B-v2

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasonin...

📝 text-generation 215,057
OpenMuQ

OpenMuQ/MuQ-large-msd-iter

No description available.

🎧 audio-classification 214,936
Qodo

Qodo/Qodo-Embed-1-1.5B

No description available.

🔗 sentence-similarity 214,742
playgroundai

playgroundai/playground-v2.5-1024px-aesthetic

Developed by: Playground - Model type: Diffusion-based text-to-image generative model - License: Playground v2.5 Community License - Summary...

🎨 text-to-image 214,687
rednote-hilab

rednote-hilab/dots.ocr

No description available.

📖 image-text-to-text 214,509
timm

timm/vit_tiny_r_s16_p8_224.augreg_in21k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 10.4 - GMACs: 0.4 - Activations (M): 1.9 - Image size: 224 ...

📸 image-classification 214,081
nvidia

nvidia/Cosmos-Reason2-8B

No description available.

📖 image-text-to-text 213,697
OpenMed

OpenMed/OpenMed-NER-PharmaDetect-BigMed-278M

No description available.

🏷️ token-classification 212,835
tohoku-nlp

tohoku-nlp/bert-base-japanese

No description available.

🎭 fill-mask 212,798
Qwen

Qwen/Qwen2.5-VL-3B-Instruct-AWQ

No description available.

📖 image-text-to-text 212,714
Shushant

Shushant/nepaliBERT

Pretraining done on bert base architecture....

🎭 fill-mask 212,547
Qwen

Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4

No description available.

📝 text-generation 212,244
stable-diffusion-v1-5

stable-diffusion-v1-5/stable-diffusion-inpainting

Developed by: Robin Rombach, Patrick Esser - Model type: Diffusion-based text-to-image generation model - Language(s): English - License: Th...

🎨 text-to-image 211,993
mlx-community

mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit

No description available.

✨ General AI Model 211,480
google

google/byt5-small

- multilingual - af - am - ar - az - be - bg - bn - ca - ceb - co - cs - cy - da - de - el - en - eo - es - et - eu - fa - fi - fil - fr - f...

✨ General AI Model 211,328
rhasspy

rhasspy/faster-whisper-base-int8

No description available.

✨ General AI Model 210,745
zai-org

zai-org/GLM-5

No description available.

📝 text-generation 210,176
OpenMed

OpenMed/OpenMed-NER-ChemicalDetect-ModernMed-149M

No description available.

🏷️ token-classification 209,814
OpenMed

OpenMed/OpenMed-NER-BloodCancerDetect-TinyMed-65M

No description available.

🏷️ token-classification 209,290
cyankiwi

cyankiwi/Qwen3-VL-4B-Instruct-AWQ-4bit

No description available.

📖 image-text-to-text 209,238
google

google/flan-t5-xl

No description available.

✨ General AI Model 209,222
myshell-ai

myshell-ai/MeloTTS-Japanese

No description available.

🗣️ text-to-speech 207,399
NousResearch

NousResearch/Meta-Llama-3.1-8B-Instruct

- en - de - fr - it - pt - hi - es - th pipelinetag: text-generation - facebook - meta - pytorch - llama - llama-3 extragatedprompt: " \ Rel...

📝 text-generation 207,079
microsoft

microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext

No description available.

🎭 fill-mask 206,706
intfloat

intfloat/e5-mistral-7b-instruct

- mteb - sentence-transformers - transformers - name: e5-mistral-7b-instruct results: - task: type: STS dataset: type: C-MTEB/AFQMC name: MT...

🔍 feature-extraction 206,651
Qwen

Qwen/Qwen3-8B-FP8

This repo contains the FP8 version of Qwen3-8B, which has the following features: - Type: Causal Language Models - Training Stage: Pretraini...

📝 text-generation 205,950
meta-llama

meta-llama/Llama-4-Scout-17B-16E-Instruct

libraryname: transformers - ar - de - en - es - fr - hi - id - it - pt - th - tl - vi basemodel: - meta-llama/Llama-4-Scout-17B-16E - facebo...

📖 image-text-to-text 205,474
unitary

unitary/toxic-bert

No description available.

📊 text-classification 205,127
speechbrain

speechbrain/lang-id-voxlingua107-ecapa

This is a spoken language recognition model trained on the VoxLingua107 dataset using SpeechBrain. The model uses the ECAPA-TDNN architectur...

🎧 audio-classification 205,123