Discover the Best AI Models

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

Model Index 55939 Total

knc6

knc6/diffractgpt_mistral_chemical_formula

No description available.

📝 text-generation 147,083
mrm8488

mrm8488/bert-tiny-finetuned-sms-spam-detection

No description available.

📊 text-classification 147,058
timm

timm/resnet50.fb_swsl_ig1b_ft_in1k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 25.6 - GMACs: 4.1 - Activations (M): 11.1 - Image size: 224...

📸 image-classification 146,850
Qwen

Qwen/Qwen3Guard-Gen-0.6B

No description available.

📝 text-generation 146,827
casperhansen

casperhansen/deepseek-coder-v2-instruct-awq

No description available.

📝 text-generation 146,804
unsloth

unsloth/Qwen3-4B-Base

Qwen3-4B-Base has the following features: - Type: Causal Language Models - Training Stage: Pretraining - Number of Parameters: 4.0B - Number...

📝 text-generation 146,647
HuggingFaceM4

HuggingFaceM4/tiny-random-LlamaForCausalLM

No description available....

📝 text-generation 146,516
timm

timm/convnext_base.fb_in22k_ft_in1k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 88.6 - GMACs: 15.4 - Activations (M): 28.8 - Image size: tr...

📸 image-classification 146,457
mistralai

mistralai/Mixtral-8x7B-v0.1

The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mistral-8x7B outperforms Llama 2 70B o...

✨ General AI Model 146,455
BAAI

BAAI/AltCLIP

No description available.

🎯 zero-shot-image-classification 146,390
TheBloke

TheBloke/Mistral-7B-Instruct-v0.2-AWQ

basemodel: mistralai/Mistral-7B-Instruct-v0.2 inference: false modelcreator: Mistral AI modelname: Mistral 7B Instruct v0.2 modeltype: mistr...

📝 text-generation 146,351
depth-anything

depth-anything/Depth-Anything-V2-Large-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 145,958
TheBloke

TheBloke/Nous-Hermes-2-Yi-34B-AWQ

Nous Hermes 2 - Yi-34B is a state of the art Yi Fine-tune. Nous Hermes 2 Yi 34B was trained on 1,000,000 entries of primarily GPT-4 generate...

📝 text-generation 145,806
stabilityai

stabilityai/sd-vae-ft-mse

No description available.

✨ General AI Model 145,743
ibm-granite

ibm-granite/granite-docling-258M

Granite Docling is a multimodal Image-Text-to-Text model engineered for efficient document conversion. It preserves the core features of Doc...

📖 image-text-to-text 145,134
trl-internal-testing

trl-internal-testing/tiny-LlavaForConditionalGeneration

No description available.

📖 image-text-to-text 145,008
Gensyn

Gensyn/Qwen2.5-0.5B-Instruct

No description available.

📝 text-generation 144,923
Wan-AI

Wan-AI/Wan2.2-T2V-A14B-Diffusers

No description available.

🎦 text-to-video 144,864
UBC-NLP

UBC-NLP/MARBERTv2

MARBERTv2 is one of three models described in our ACL 2021 paper "ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic". We find tha...

🎭 fill-mask 144,650
unsloth

unsloth/Qwen3.5-35B-A3B-Experiments-GGUF

No description available....

✨ General AI Model 144,610
John6666

John6666/prefect-illustrious-xl-v3-sdxl

Original model is here. This model created by GoofyAi....

🎨 text-to-image 144,321
jinaai

jinaai/jina-embeddings-v5-text-small-retrieval

`jina-embeddings-v5-text-small-retrieval` is a compact, high-performance text embedding model designed for information retrieval. It is part...

🔗 sentence-similarity 144,135
TahaDouaji

TahaDouaji/detr-doc-table-detection

detr-doc-table-detection is a model trained to detect both Bordered and Borderless tables in documents, based on facebook/detr-resnet-50. - ...

👁️ object-detection 143,912
Qwen

Qwen/Qwen3.5-2B

Type: Causal Language Model with Vision Encoder - Training Stage: Pre-training & Post-training - Language Model - Number of Parameters: 2B -...

📖 image-text-to-text 143,887
Comfy-Org

Comfy-Org/stable-diffusion-v1-5-archive

No description available.

✨ General AI Model 143,885
DeepBeepMeep

DeepBeepMeep/LTX-2

No description available.

✨ General AI Model 143,489
optimum-intel-internal-testing

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

No description available.

🎨 text-to-image 143,482
Qwen

Qwen/Qwen3-VL-235B-A22B-Instruct-FP8

No description available.

📖 image-text-to-text 143,385
qylu4156

qylu4156/strongreject-15k-v1

No description available.

✨ General AI Model 143,303
facebook

facebook/dinov3-vits16-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 143,268
Marxav

Marxav/wav2vec2-large-xlsr-53-breton

The model can be used directly (without a language model) as follows: ```python import torch import torchaudio from datasets import loaddata...

🎙️ automatic-speech-recognition 143,218
google

google/translategemma-4b-it

No description available.

📖 image-text-to-text 142,998
Yuxihenry

Yuxihenry/SpatialTrackerV2_Front

No description available.

✨ General AI Model 142,092
vikp

vikp/surya_layout3

No description available.

✨ General AI Model 141,813
Qwen

Qwen/Qwen2.5-VL-72B-Instruct-AWQ

No description available.

📖 image-text-to-text 141,442
BigDannyPt

BigDannyPt/Illustrious-GGUF-Collection

No description available.

✨ General AI Model 141,343
swiss-ai

swiss-ai/Apertus-8B-Instruct-2509

basemodel: - swiss-ai/Apertus-8B-2509 pipelinetag: text-generation libraryname: transformers - multilingual - compliant - swiss-ai - apertus...

📝 text-generation 141,305
timm

timm/vit_base_patch16_dinov3.lvd1689m

Model Type: Image Feature Encoder - Model Stats: - Params (M): 85.6 - GMACs: 23.6 - Activations (M): 34.1 - Image size: 256 x 256 - Original...

🔎 image-feature-extraction 140,987
trl-internal-testing

trl-internal-testing/tiny-CohereForCausalLM

No description available.

📝 text-generation 140,839
timm

timm/tf_mobilenetv3_large_minimal_100.in1k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 3.9 - GMACs: 0.2 - Activations (M): 4.4 - Image size: 224 x...

📸 image-classification 140,751
nvidia

nvidia/canary-qwen-2.5b

No description available.

🎙️ automatic-speech-recognition 140,748
Systran

Systran/faster-distil-whisper-large-v3

No description available.

🎙️ automatic-speech-recognition 140,262
facebook

facebook/dinov2-giant

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

🔎 image-feature-extraction 139,919
vikp

vikp/surya_tablerec

No description available.

✨ General AI Model 139,790
optimum-intel-internal-testing

optimum-intel-internal-testing/tiny-random-t5

No description available....

✨ General AI Model 139,784
Alimzhan

Alimzhan/wav2vec2-large-xls-r-300m-albanian-colab

More information needed...

🎙️ automatic-speech-recognition 139,711
sesame

sesame/csm-1b

No description available.

🗣️ text-to-speech 139,570
Jean-Baptiste

Jean-Baptiste/camembert-ner

No description available.

🏷️ token-classification 139,516
HuggingFaceTB

HuggingFaceTB/SmolVLM2-2.2B-Instruct

No description available.

📖 image-text-to-text 139,404
timm

timm/tf_mobilenetv3_small_minimal_100.in1k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 2.0 - GMACs: 0.1 - Activations (M): 1.4 - Image size: 224 x...

📸 image-classification 139,330