Discover the Best AI Models
Search, analyze, and download from our global directory of 3,000+ open-source models.
Model Index 55939 Total
soleimanian/financial-roberta-large-sentiment
No description available.
Helsinki-NLP/opus-mt-ar-en
No description available.
tiiuae/falcon-7b
No description available.
HuggingFaceTB/SmolVLM2-256M-Video-Instruct
No description available.
lmstudio-community/gemma-3n-E4B-it-MLX-8bit
No description available.
microsoft/infoxlm-large
InfoXLM (NAACL 2021, paper, repo, model) InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training....
lmstudio-community/gemma-3n-E4B-it-MLX-bf16
No description available.
OpenMed/OpenMed-NER-PharmaDetect-BioPatient-108M
No description available.
IAMJB/RadEvalModernBERT
Inference:...
lmstudio-community/gemma-3n-E4B-it-MLX-6bit
No description available.
trl-internal-testing/tiny-Gemma3ForConditionalGeneration
No description available.
OpenGVLab/InternVL3-1B-hf
No description available.
ai-forever/kandinsky-videomae-large-camera-motion
VideoMAE model(`large`) variant that has been finetuned for multi-label video classification (a video can belong to multiple classes simulta...
internlm/internlm2-1_8b-reward
No description available.
sociocom/MedNER-CR-JA
No description available.
TheDrummer/Gemmasutra-Mini-2B-v1-GGUF
No description available.
wan-world/Wan2.1-2.2
You will find here all the Wan 2.1 Video models used with WanGP (https://github.com/deepbeepmeep/Wan2GP) :...
microsoft/layoutlm-base-uncased
LayoutLM is a simple but effective pre-training method of text and layout for document image understanding and information extraction tasks,...
trl-internal-testing/tiny-MistralForCausalLM-0.1
No description available.
watt-ai/watt-tool-8B
This model is specifically designed to excel at complex tool usage scenarios that require multi-turn interactions, making it ideal for empow...
minishlab/potion-base-32M
libraryname: model2vec - name: potion-base-32M results: - dataset: config: en-ext name: MTEB AmazonCounterfactualClassification (en-ext) rev...
Xenova/bge-small-en-v1.5
No description available.
timm/vit_base_patch32_clip_224.laion400m_e32
dataset: LAION-400M...
sentence-transformers/stsb-xlm-r-multilingual
No description available.
OpenMed/OpenMed-NER-PharmaDetect-BigMed-560M
No description available.
unslothai/vram-80
No description available.
cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit
No description available.
DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF
No description available.
Rostlab/prot_t5_xl_half_uniref50-enc
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...
LiquidAI/LFM2.5-VL-1.6B-GGUF
No description available.
Comfy-Org/Lumina_Image_2.0_Repackaged
Lumina Image 2.0 checkpoint repackaged for ComfyUI use....
FluidInference/parakeet-tdt-0.6b-v3-coreml
Architecture: Parakeet TDT v3 (Token Duration Transducer, 0.6B parameters) - Input audio: 16 kHz, mono, Float32 PCM in range [-1, 1] - Langu...
jitesh/emotion-english
- en pipelinetag: text-classification - emotion - 20 classes - code - emotions - text: I'm so angry right now. I can't believe he did that t...
ai-forever/ru-en-RoSBERTa
- name: ru-en-RoSBERTa results: - dataset: config: default name: MTEB CEDRClassification (default) revision: c0ba03d058e3e1b2f3fd20518875a45...
myshell-ai/MeloTTS-Chinese
No description available.
meta-llama/Llama-2-13b-chat-hf
Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the website and ...
trl-internal-testing/tiny-GemmaForCausalLM
No description available.
unsloth/Qwen3-0.6B-GGUF
Qwen3-0.6B has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: ...
trl-internal-testing/tiny-Phi3ForCausalLM
No description available.
mistral-labs/pixtral-12b
No description available.
LiquidAI/LFM2.5-1.2B-Instruct
No description available.
hiiamsid/sentence_similarity_spanish_es
No description available.
shi-labs/oneformer_coco_swin_large
OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architect...
livekit/turn-detector
No description available.
avichr/heBERT_NER
HeBERT is a Hebrew pretrained language model. It is based on Google's BERT architecture and it is BERT-Base config....
avsolatorio/GIST-Embedding-v0
- en libraryname: sentence-transformers pipelinetag: sentence-similarity - feature-extraction - mteb - sentence-similarity - sentence-transf...
breezedeus/pix2text-mfr
This MFR model utilizes the TrOCR architecture developed by Microsoft, starting with its initial values and retrained using a dataset of mat...
zai-org/GLM-4.7-FP8
No description available.
Profluent-Bio/E1-600m
No description available.
naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B
No description available.