Discover the Best AI Models

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

Model Index 55939 Total

SWivid

SWivid/E2-TTS

No description available.

🗣️ text-to-speech 112,403
vinai

vinai/bartpho-syllable

No description available.

🔍 feature-extraction 112,356
NX-AI

NX-AI/TiRex

No description available.

🕒 time-series-forecasting 112,096
google

google/reformer-crime-and-punishment

Crime and Punishment is a novel written by Fyodor Dostoevsky and was translated into English....

📝 text-generation 112,090
google

google/gemma-7b

No description available.

📝 text-generation 112,039
kuleshov-group

kuleshov-group/mdlm-owt

The model, which has a context length of `1024` and is similar in size to GPT2-medium with approximately `130 million` non-embedding paramet...

🎭 fill-mask 112,034
Qwen

Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8

No description available.

📝 text-generation 111,896
optimum-intel-internal-testing

optimum-intel-internal-testing/stable-diffusion-3-tiny-random

No description available.

🎨 text-to-image 111,755
google

google/vit-base-patch16-384

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, ...

📸 image-classification 111,655
mlx-community

mlx-community/Llama-3.2-1B-Instruct-4bit

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

📝 text-generation 111,605
weiweishi

weiweishi/roc-bert-base-zh

No description available.

🎭 fill-mask 111,580
flaubert

flaubert/flaubert_base_cased

No description available.

🎭 fill-mask 111,552
google

google/rembert

RemBERT's main difference with mBERT is that the input and output embeddings are not tied. Instead, RemBERT uses small input embeddings and ...

✨ General AI Model 111,379
jeffcookio

jeffcookio/granite-3.3-8b-instruct-gptqmodel-4b-64g

No description available.

✨ General AI Model 111,085
huggyllama

huggyllama/llama-7b

No description available.

📝 text-generation 111,067
stas

stas/tiny-wmt19-en-de

No description available.

✨ General AI Model 110,916
uclanlp

uclanlp/plbart-base

No description available....

✨ General AI Model 110,907
microsoft

microsoft/speecht5_tts

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-m...

🗣️ text-to-speech 110,885
OpenMed

OpenMed/OpenMed-NER-PharmaDetect-SuperMedical-125M

No description available.

🏷️ token-classification 110,811
typeform

typeform/distilbert-base-uncased-mnli

Model Description: This is the uncased DistilBERT model fine-tuned on Multi-Genre Natural Language Inference (MNLI) dataset for the zero-sho...

🎯 zero-shot-classification 110,590
HuggingFaceH4

HuggingFaceH4/zephyr-7b-beta

Model type: A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets. - Language(s) (NLP): Primarily Engl...

📝 text-generation 110,533
studio-ousia

studio-ousia/luke-base

No description available.

🎭 fill-mask 110,398
OpenMed

OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M

No description available.

🏷️ token-classification 110,379
microsoft

microsoft/prophetnet-large-uncased

No description available.

✨ General AI Model 110,362
OpenMed

OpenMed/OpenMed-NER-GenomeDetect-PubMed-109M

No description available.

🏷️ token-classification 110,290
google

google/bert_for_seq_generation_L-24_bbc_encoder

No description available....

✨ General AI Model 110,236
EleutherAI

EleutherAI/pythia-6.9b-deduped

Developed by: EleutherAI - Model type: Transformer-based Language Model - Language: English - Learn more: Pythia's GitHub repository for tra...

📝 text-generation 110,230
nphSi

nphSi/Z-Image-Lora

+ Always use full LoRa name with "vrtlxxxx" trigger in prompt like "Alba Baptista (vrtlalbabaptista) in a swimming pool". "Woman" or "1girl"...

🎨 text-to-image 110,199
Qwen

Qwen/Qwen2-1.5B

Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language mod...

📝 text-generation 110,180
nm-testing

nm-testing/Llama3_2_1B_speculator.eagle3

No description available....

✨ General AI Model 110,178
Sehyo

Sehyo/Qwen3.5-122B-A10B-NVFP4

No description available.

📖 image-text-to-text 110,152
warshanks

warshanks/Jan-nano-AWQ

Note: Jan-Nano is a non-thinking model....

📝 text-generation 110,127
unsloth

unsloth/MiniMax-M2.5-GGUF

To Run MiniMax-M2.5 locally - Read our Guide! Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants....

📝 text-generation 110,101
Rostlab

Rostlab/prot_t5_xl_uniref50

ProtT5-XL-UniRef50 is based on the `t5-3b` model and was pretrained on a large corpus of protein sequences in a self-supervised fashion. Thi...

✨ General AI Model 110,018
bosonai

bosonai/hubert_base

No description available.

✨ General AI Model 109,988
MaziyarPanahi

MaziyarPanahi/DeepSeek-R1-0528-Qwen3-8B-GGUF

- Model creator: deepseek-ai - Original model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B...

📝 text-generation 109,948
facebook

facebook/dinov3-vith16plus-pretrain-lvd1689m

These are Vision Transformer and ConvNeXt models trained following the method described in the DINOv3 paper. 12 models are provided: - 10 mo...

🔎 image-feature-extraction 109,803
MaziyarPanahi

MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF

- Model creator: mistralai - Original model: mistralai/Mistral-7B-Instruct-v0.3...

📝 text-generation 109,625
lmstudio-community

lmstudio-community/MiniMax-M2.5-MLX-4bit

No description available.

📝 text-generation 109,557
Qwen

Qwen/Qwen3-30B-A3B-FP8

This repo contains the FP8 version of Qwen3-30B-A3B, which has the following features: - Type: Causal Language Models - Training Stage: Pret...

📝 text-generation 109,477
facebook

facebook/blenderbot_small-90M

+ Paper: Recipes for building an open-domain chatbot + Original PARLAI Code...

✨ General AI Model 109,021
alibaba-damo

alibaba-damo/mgp-str-base

MGP-STR is pure vision STR model, consisting of ViT and specially designed A^3 modules. The ViT module was initialized from the weights of D...

🖼️ image-to-text 108,960
unsloth

unsloth/embeddinggemma-300m

No description available.

🔗 sentence-similarity 108,878
junnyu

junnyu/roformer_chinese_small

https://github.com/ZhuiyiTechnology/roformer...

🎭 fill-mask 108,873
ales

ales/wav2vec2-cv-be

No description available.

🎙️ automatic-speech-recognition 108,491
susnato

susnato/clvp_dev

DISCLAIMER : I do not own any weights present in this repository. All weights belong to the author of the paper - "Better speech synthesis t...

🔍 feature-extraction 108,455
nvidia

nvidia/mit-b0

SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...

📸 image-classification 108,302
microsoft

microsoft/speecht5_asr

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-m...

🎙️ automatic-speech-recognition 108,194
deepseek-community

deepseek-community/Janus-Pro-1B

No description available.

🌌 any-to-any 108,172
facebook

facebook/mbart-large-en-ro

- translation...

🌐 translation 108,122