Discover the Best AI Models
Search, analyze, and download from our global directory of 3,000+ open-source models.
Model Index 55939 Total
nvidia/parakeet-tdt-1.1b
- en libraryname: nemo - librispeechasr - fishercorpus - Switchboard-1 - WSJ-0 - WSJ-1 - National-Singapore-Corpus-Part-1 - National-Singapo...
evamxb/dev-author-em-clf
More information needed...
Qwen/Qwen3-ForcedAligner-0.6B
No description available.
lmstudio-community/MiniMax-M2.5-MLX-8bit
No description available.
j-hartmann/sentiment-roberta-large-english-3-classes
- roberta - sentiment - twitter...
peft-internal-testing/tiny-dummy-qwen2
No description available.
OpenMed/OpenMed-NER-ChemicalDetect-PubMed-335M
No description available.
vidore/colqwen2-v0.1
No description available.
emrecan/bert-base-turkish-cased-mean-nli-stsb-tr
No description available.
John6666/nova-furry-xl-il-v120-sdxl
Original model is here. This model created by Crody....
nvidia/Kimi-K2-Thinking-NVFP4
No description available.
mlx-community/all-MiniLM-L6-v2-4bit
No description available.
pparasurama/raceBERT-ethnicity
No description available....
ibm-granite/granite-speech-3.3-8b
No description available.
OpenGVLab/InternVL3-8B-Instruct
No description available.
llava-hf/llava-interleave-qwen-0.5b-hf
Model type: LLaVA Interleave is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-re...
vennify/t5-base-grammar-correction
No description available.
QuantStack/Wan2.2-T2V-A14B-GGUF
No description available.
facebook/s2t-small-librispeech-asr
S2T is an end-to-end sequence-to-sequence transformer model. It is trained with standard autoregressive cross-entropy loss and generates the...
iarfmoose/bert-base-cased-qa-evaluator
This model takes a question answer pair as an input and outputs a value representing its prediction about whether the input was a valid ques...
Salesforce/ctrl
No description available.
RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16
Model Architecture: Meta-Llama-3 - Input: Text - Output: Text - Model Optimizations: - Weight quantization: INT4 - Intended Use Cases: Inten...
HuggingFaceTB/SmolLM3-3B
No description available.
dslim/bert-base-NER-uncased
No description available.
eagle618/deepseek-v3-random
No description available.
allenai/Olmo-3-7B-Instruct-SFT
No description available.
unslothai/vram-96
No description available.
typhoon-ai/typhoon-ocr-7b
No description available.
vidore/colqwen2-v1.0
No description available.
canopylabs/3b-de-ft-research_release
No description available.
watt-ai/watt-tool-70B
This model is specifically designed to excel at complex tool usage scenarios that require multi-turn interactions, making it ideal for empow...
OpenMed/OpenMed-NER-PathologyDetect-PubMed-v2-109M
No description available.
littlejohn-ai/bge-m3-spa-law-qa
No description available.
google/gemma-3-270m-it
No description available.
cambridgeltl/SapBERT-from-PubMedBERT-fulltext
No description available.
nvidia/Llama-3.3-70B-Instruct-FP8
No description available.
MaziyarPanahi/Qwen3-4B-Instruct-2507-GGUF
- Model creator: Qwen - Original model: Qwen/Qwen3-4B-Instruct-2507...
MaziyarPanahi/gemma-3-4b-it-GGUF
- Model creator: google - Original model: google/gemma-3-4b-it...
EleutherAI/gpt-neo-125m
GPT-Neo 125M is a transformer model designed using EleutherAI's replication of the GPT-3 architecture. GPT-Neo refers to the class of models...
depth-anything/Depth-Anything-V2-Large
No description available.
FacebookAI/xlm-mlm-en-2048
The XLM model was proposed in Cross-lingual Language Model Pretraining by Guillaume Lample and Alexis Conneau. It’s a transformer pretrained...
mlx-community/gemma-3-27b-it-qat-4bit
No description available.
AI-Sweden-Models/gpt-sw3-126m
AI Sweden Base models GPT-Sw3 126M | GPT-Sw3 356M | GPT-Sw3 1.3B GPT-Sw3 6.7B | GPT-Sw3 6.7B v2 | GPT-Sw3 20B GPT-Sw3 40B Instruct models GP...
google/owlv2-large-patch14-ensemble
The OWLv2 model (short for Open-World Localization) was proposed in Scaling Open-Vocabulary Object Detection by Matthias Minderer, Alexey Gr...
sentence-transformers/sentence-t5-base
No description available.
refactai/Refact-1_6B-fim
pipelinetag: text-generation inference: true - text: 'def printhelloworld():' exampletitle: Hello world group: Python pretrain-datasets: - b...
funnel-transformer/small
Funnel Transformer is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pret...
shibing624/text2vec-base-multilingual
pipelinetag: sentence-similarity libraryname: sentence-transformers - sentence-transformers - feature-extraction - sentence-similarity - tra...
albert/albert-base-v1
ALBERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on th...
timm/tf_efficientnetv2_m.in21k_ft_in1k
Model Type: Image classification / feature backbone - Model Stats: - Params (M): 54.1 - GMACs: 15.9 - Activations (M): 57.5 - Image size: tr...