Discover the Best AI Models

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

Model Index 55939 Total

deepseek-ai

deepseek-ai/DeepSeek-OCR-2

No description available.

📖 image-text-to-text 1,640,793
Qwen

Qwen/Qwen2-VL-7B-Instruct

No description available.

📖 image-text-to-text 1,634,324
Qwen

Qwen/Qwen2.5-Coder-7B-Instruct

No description available.

📝 text-generation 1,626,050
Alibaba-NLP

Alibaba-NLP/gte-large-en-v1.5

- allenai/c4 libraryname: transformers - sentence-transformers - gte - mteb - transformers.js - sentence-similarity - en - name: gte-large-e...

🔗 sentence-similarity 1,607,736
apple

apple/OpenELM-1_1B-Instruct

No description available.

📝 text-generation 1,599,430
kingabzpro

kingabzpro/wav2vec2-large-xls-r-300m-Urdu

No description available.

🎙️ automatic-speech-recognition 1,590,162
dslim

dslim/bert-base-NER

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

🏷️ token-classification 1,583,329
Qwen

Qwen/Qwen2.5-32B

No description available.

📝 text-generation 1,569,598
Freepik

Freepik/nsfw_image_detector

This model is a vision transformer based on the EVA architecture, fine-tuned for NSFW content classification. It has been trained to detect ...

📸 image-classification 1,566,580
mistralai

mistralai/Mistral-7B-Instruct-v0.3

No description available.

✨ General AI Model 1,564,237
facebook

facebook/bart-base

BART is a transformer encoder-decoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BAR...

🔍 feature-extraction 1,546,931
lpiccinelli

lpiccinelli/unik3d-vitl

No description available.

✨ General AI Model 1,544,551
stable-diffusion-v1-5

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

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

🎨 text-to-image 1,544,501
facebook

facebook/wav2vec2-base

No description available.

✨ General AI Model 1,542,853
gigant

gigant/romanian-wav2vec2

The architecture is based on facebook/wav2vec2-xls-r-300m with a speech recognition CTC head and an added 5-gram language model (using pyctc...

🎙️ automatic-speech-recognition 1,528,073
distilbert

distilbert/distilroberta-base

No description available.

🎭 fill-mask 1,524,509
Xenova

Xenova/bge-base-en-v1.5

No description available.

🔍 feature-extraction 1,523,090
facebook

facebook/esm2_t33_650M_UR50D

No description available.

🎭 fill-mask 1,506,273
deepseek-ai

deepseek-ai/DeepSeek-V3

No description available.

📝 text-generation 1,494,494
google

google/gemma-3-27b-it

No description available.

📖 image-text-to-text 1,493,679
Qwen

Qwen/Qwen3-VL-4B-Instruct

No description available.

📖 image-text-to-text 1,482,594
prajjwal1

prajjwal1/bert-tiny

No description available.

✨ General AI Model 1,479,924
meta-llama

meta-llama/Llama-3.2-1B

- en - de - fr - it - pt - hi - es - th libraryname: transformers pipelinetag: text-generation - facebook - meta - pytorch - llama - llama-3...

📝 text-generation 1,474,173
deepseek-ai

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

No description available.

📝 text-generation 1,466,870
timm

timm/mobilenetv3_large_100.ra_in1k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 5.5 - GMACs: 0.2 - Activations (M): 4.4 - Image size: 224 x...

📸 image-classification 1,455,740
Harveenchadha

Harveenchadha/vakyansh-wav2vec2-tamil-tam-250

No description available.

🎙️ automatic-speech-recognition 1,448,478
nvidia

nvidia/bigvgan_v2_22khz_80band_256x

No description available.

🎛️ audio-to-audio 1,445,270
thenlper

thenlper/gte-large

- mteb - sentence-similarity - sentence-transformers - Sentence Transformers - name: gte-large results: - task: type: Classification dataset...

🔗 sentence-similarity 1,436,019
intfloat

intfloat/e5-base-v2

- mteb - Sentence Transformers - sentence-similarity - sentence-transformers - name: e5-base-v2 results: - task: type: Classification datase...

🔗 sentence-similarity 1,428,274
nvidia

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8

Model Developer: NVIDIA Corporation Model Dates: September 2025 \- December 2025 Data Freshness: The post-training data has a cutoff date of...

📝 text-generation 1,427,762
bardsai

bardsai/finance-sentiment-ja-base

No description available.

📊 text-classification 1,416,334
meta-llama

meta-llama/Llama-3.2-3B

- en - de - fr - it - pt - hi - es - th libraryname: transformers pipelinetag: text-generation - facebook - meta - pytorch - llama - llama-3...

📝 text-generation 1,414,722
answerdotai

answerdotai/answerai-colbert-small-v1

No description available.

✨ General AI Model 1,409,943
roadz

roadz/qwen3-1.7b-oxxroad

This repository follows the structure of a Qwen3-style causal language model on Hugging Face. It includes model configuration, tokenizer ass...

✨ General AI Model 1,383,864
microsoft

microsoft/wavlm-base-plus

No description available.

🔍 feature-extraction 1,380,388
meta-llama

meta-llama/Meta-Llama-3-8B-Instruct

Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned genera...

📝 text-generation 1,377,777
facebook

facebook/musicgen-medium

Organization developing the model: The FAIR team of Meta AI. Model date: MusicGen was trained between April 2023 and May 2023. Model version...

✨ text-to-audio 1,369,571
meta-llama

meta-llama/Llama-3.1-8B

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

📝 text-generation 1,368,085
lengyue233

lengyue233/content-vec-best

No description available.

✨ General AI Model 1,364,093
KBLab

KBLab/wav2vec2-large-voxrex-swedish

No description available.

🎙️ automatic-speech-recognition 1,359,384
StanfordAIMI

StanfordAIMI/stanford-deidentifier-base

Stanford de-identifier was trained on a variety of radiology and biomedical documents with the goal of automatising the de-identification pr...

🏷️ token-classification 1,354,910
openvla

openvla/openvla-7b

No description available.

🦾 robotics 1,346,461
depth-anything

depth-anything/Depth-Anything-V2-Small-hf

Depth Anything V2 leverages the DPT architecture with a DINOv2 backbone. The model is trained on ~600K synthetic labeled images and ~62 mill...

📏 depth-estimation 1,345,520
Qwen

Qwen/Qwen3.5-397B-A17B

Type: Causal Language Model with Vision Encoder - Training Stage: Pre-training & Post-training - Language Model - Number of Parameters: 397B...

📖 image-text-to-text 1,338,447
dbmdz

dbmdz/bert-large-cased-finetuned-conll03-english

No description available....

🏷️ token-classification 1,336,109
hmellor

hmellor/tiny-random-LlamaForCausalLM

No description available.

📝 text-generation 1,336,028
google

google/gemma-3-12b-it

No description available.

📖 image-text-to-text 1,334,645
nguyenvulebinh

nguyenvulebinh/wav2vec2-base-vi-vlsp2020

Our models use wav2vec2 architecture, pre-trained on 13k hours of Vietnamese youtube audio (un-label data) and fine-tuned on 250 hours label...

🎙️ automatic-speech-recognition 1,328,043
Qwen

Qwen/Qwen2.5-Coder-0.5B-Instruct

No description available.

📝 text-generation 1,311,734
Qwen

Qwen/Qwen3-VL-Embedding-2B

Qwen3-VL-Embedding-2B has the following features: - Model Type: MultiModal Embedding - Supported Languages: 30+ Languages - Supported Input ...

🔍 feature-extraction 1,307,234
3 4 5 6 7