Discover the Best AI Models

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

Model Index 55939 Total

microsoft

microsoft/deberta-base

No description available.

🎭 fill-mask 1,305,906
thenlper

thenlper/gte-base

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

🔗 sentence-similarity 1,304,285
bigscience

bigscience/bloomz-560m

- bigscience/xP3 - ak - ar - as - bm - bn - ca - code - en - es - eu - fon - fr - gu - hi - id - ig - ki - kn - lg - ln - ml - mr - ne - nso...

📝 text-generation 1,303,887
jonatasgrosman

jonatasgrosman/wav2vec2-large-xlsr-53-persian

No description available.

🎙️ automatic-speech-recognition 1,299,243
airesearch

airesearch/wav2vec2-large-xlsr-53-th

No description available.

🎙️ automatic-speech-recognition 1,298,490
NovaSearch

NovaSearch/stella_en_400M_v5

- name: stellaen400Mv5 results: - dataset: config: en name: MTEB AmazonCounterfactualClassification (en) revision: e8379541af4e31359cca9fbcf...

🔗 sentence-similarity 1,290,182
bullpoint

bullpoint/Qwen3-Coder-Next-AWQ-4bit

Qwen3-Coder-Next has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parame...

📝 text-generation 1,288,011
mesolitica

mesolitica/wav2vec2-xls-r-300m-mixed

No description available.

🎙️ automatic-speech-recognition 1,264,671
autogluon

autogluon/chronos-2-small

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

🕒 time-series-forecasting 1,259,263
prithivida

prithivida/parrot_paraphraser_on_T5

No description available.

✨ General AI Model 1,252,531
Qwen

Qwen/Qwen3-Next-80B-A3B-Instruct

> [!Note] > Qwen3-Next-80B-A3B-Instruct supports only instruct (non-thinking) mode and does not generate ```` blocks in its output. Qwen3-Ne...

📝 text-generation 1,240,316
intfloat

intfloat/e5-small-v2

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

🔗 sentence-similarity 1,229,492
unslothai

unslothai/1

No description available.

🔍 feature-extraction 1,223,258
autogluon

autogluon/chronos-bolt-mini

No description available.

🕒 time-series-forecasting 1,221,455
google

google/vit-base-patch16-224-in21k

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

🔎 image-feature-extraction 1,218,566
distil-whisper

distil-whisper/distil-large-v3

Distil-Whisper inherits the encoder-decoder architecture from Whisper. The encoder maps a sequence of speech vector inputs to a sequence of ...

🎙️ automatic-speech-recognition 1,216,096
nlptown

nlptown/bert-base-multilingual-uncased-sentiment

- en - nl - de - fr - it - es...

📊 text-classification 1,214,774
Qwen

Qwen/Qwen3-30B-A3B

Qwen3-30B-A3B has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameter...

📝 text-generation 1,210,375
nomic-ai

nomic-ai/nomic-embed-text-v2-moe

`nomic-embed-text-v2-moe` is a SoTA multilingual MoE text embedding model that excels at multilingual retrieval: - High Performance: SoTA Mu...

🔗 sentence-similarity 1,208,325
sentence-transformers

sentence-transformers/distiluse-base-multilingual-cased-v2

No description available.

🔗 sentence-similarity 1,205,075
laion

laion/larger_clap_general

No description available.

🔍 feature-extraction 1,198,508
google

google/siglip-base-patch16-224

SigLIP is CLIP, a multimodal model, with a better loss function. The sigmoid loss operates solely on image-text pairs and does not require a...

🎯 zero-shot-image-classification 1,191,101
Qwen

Qwen/Qwen2.5-0.5B

No description available.

📝 text-generation 1,189,562
unslothai

unslothai/repeat

No description available.

🔍 feature-extraction 1,178,628
microsoft

microsoft/Florence-2-large

No description available.

📖 image-text-to-text 1,172,282
Comfy-Org

Comfy-Org/Qwen-Image-Edit_ComfyUI

No description available.

✨ General AI Model 1,169,202
Qwen

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

No description available.

📝 text-generation 1,156,750
timm

timm/convnext_tiny.fb_in22k

Model Type: Image classification / feature backbone - Model Stats: - Params (M): 44.6 - GMACs: 4.5 - Activations (M): 13.5 - Image size: 224...

📸 image-classification 1,149,807
hubertsiuzdak

hubertsiuzdak/snac_24khz

No description available.

✨ General AI Model 1,137,920
trl-internal-testing

trl-internal-testing/tiny-Qwen2ForSequenceClassification-2.5

No description available.

📊 text-classification 1,137,322
facebook

facebook/dinov2-base

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 1,132,921
Qwen

Qwen/Qwen2.5-14B-Instruct-AWQ

No description available.

📝 text-generation 1,132,830
Alibaba-NLP

Alibaba-NLP/gte-multilingual-base

- mteb - sentence-transformers - transformers - multilingual - sentence-similarity - text-embeddings-inference - af - ar - az - be - bg - bn...

🔗 sentence-similarity 1,130,868
Qwen

Qwen/Qwen2-VL-7B-Instruct-AWQ

No description available.

📖 image-text-to-text 1,115,503
facebook

facebook/roberta-hate-speech-dynabench-r4-target

No description available.

📊 text-classification 1,115,350
timm

timm/efficientnet_b0.ra_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 1,113,290
mixedbread-ai

mixedbread-ai/mxbai-rerank-xsmall-v1

No description available.

🏆 text-ranking 1,110,801
gerbejon

gerbejon/segformer-websegcl25-2000-mc-v2

No description available.

✨ General AI Model 1,110,733
cross-encoder

cross-encoder/ms-marco-MiniLM-L12-v2

No description available.

🏆 text-ranking 1,109,733
Qwen

Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4

No description available.

📝 text-generation 1,108,851
sentence-transformers

sentence-transformers/multi-qa-MiniLM-L6-cos-v1

No description available.

🔗 sentence-similarity 1,106,415
ibm-granite

ibm-granite/granite-embedding-small-english-r2

Developed by: Granite Embedding Team, IBM - Repository: ibm-granite/granite-embedding-models - Project Page: IBM Granite - Paper: Granite Em...

🔍 feature-extraction 1,106,032
ggml-org

ggml-org/tinygemma3-GGUF

No description available.

✨ General AI Model 1,104,621
sentence-transformers

sentence-transformers/paraphrase-MiniLM-L3-v2

No description available.

🔗 sentence-similarity 1,103,781
thomas-sounack

thomas-sounack/BioClinical-ModernBERT-base

No description available.

🎭 fill-mask 1,102,378
google-bert

google-bert/bert-base-chinese

No description available.

🎭 fill-mask 1,097,261
mixedbread-ai

mixedbread-ai/mxbai-rerank-base-v1

No description available.

🏆 text-ranking 1,085,469
RedHatAI

RedHatAI/Qwen2.5-1.5B-quantized.w8a8

Model Architecture: Qwen2 - Input: Text - Output: Text - Model Optimizations: - Activation quantization: INT8 - Weight quantization: INT8 - ...

📝 text-generation 1,084,672
OpenGVLab

OpenGVLab/InternVL2-2B

InternVL 2.0 is a multimodal large language model series, featuring models of various sizes. For each size, we release instruction-tuned mod...

📖 image-text-to-text 1,081,198
Qwen

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

No description available.

🗣️ text-to-speech 1,080,797
4 5 6 7 8