Optimum Intel documentation
Supported models
Supported models
🤗 Optimum handles the export of models to OpenVINO in the exporters.openvino module. It provides classes, functions, and a command line interface to perform the export easily.
Here is the list of the supported architectures :
Transformers
- Albert
 - Aquila
 - Aquila 2
 - Arcee
 - Arctic
 - Audio Spectrogram Transformer
 - Baichuan 2
 - Bart
 - Beit
 - Bert
 - BioGPT
 - BlenderBot
 - BlenderBotSmall
 - Bloom
 - CLIP
 - Camembert
 - ChatGLM (ChatGLM2, ChatGLM3, GLM4)
 - CodeGen
 - CodeGen2
 - Cohere
 - ConvBert
 - ConvNext
 - DBRX
 - Data2VecAudio
 - Data2VecText
 - Data2VecVision
 - Deberta
 - Deberta-v2
 - DeciLM
 - Deit
 - Deepseek
 - Deepseek_v2
 - Deepseek_v3
 - DistilBert
 - Ernie4.5
 - Electra
 - Encoder Decoder
 - ESM
 - Exaone
 - Falcon
 - Falcon-Mamba
 - Flaubert
 - GLM-4
 - GLM-Edge
 - GPT-2
 - GPT-BigCode
 - GPT-J
 - GPT-Neo
 - GPT-NeoX
 - GPT-NeoX-Japanese
 - Gemma
 - Gemma2
 - Gemma3
 - GOT-OCR 2.0
 - Granite
 - GraniteMoE
 - Hubert
 - IBert
 - Idefics3
 - InternLM
 - InternLM2
 - InternVL2
 - Jais
 - Levit
 - Llama
 - Llama4
 - Llava
 - Llava-Next
 - Llava-Next-Video
 - M2-M100
 - MAIRA-2
 - Mamba
 - MBart
 - MPNet
 - MPT
 - MT5
 - Marian
 - MiniCPM
 - MiniCPM3
 - MiniCPM-o
 - MiniCPMV
 - Mistral
 - Mixtral
 - MobileBert
 - MobileNet v1
 - MobileNet v2
 - MobileVit
 - Nystromformer
 - OLMo
 - OPT
 - Orion
 - Pegasus
 - Perceiver
 - Persimmon
 - Phi
 - Phi3
 - Phi3.5-MoE
 - Phi3Vision
 - Phi4-Multimodal
 - Pix2Struct
 - PoolFormer
 - Qwen
 - Qwen2(Qwen1.5, Qwen2.5)
 - Qwen2MoE
 - Qwen2VL
 - Qwen2.5VL
 - ResNet
 - Roberta
 - Roformer
 - SAM
 - SEW
 - SEW-D
 - Segformer
 - SigLIP
 - SmolVLM(SmolVLM2)
 - SpeechT5 (text-to-speech)
 - SqueezeBert
 - StableLM
 - StarCoder2
 - Swin
 - T5
 - TROCR
 - UniSpeech
 - UniSpeech SAT
 - Vision Encoder Decoder
 - Vit
 - Wav2Vec2
 - Wav2Vec2 Conformer
 - WavLM
 - Whisper
 - XGLM
 - XLM
 - XLM-Roberta
 - XVERSE
 - Zamba2
 
Diffusers
- Stable Diffusion
 - Stable Diffusion XL
 - Latent Consistency
 - Stable Diffusion 3
 - Flux
 - Sana
 - SanaSprint
 - LTX
 
Timm
- PiT
 - ViT
 
Sentence Transformers
- All Transformer and CLIP-based models.
 
OpenCLIP
- All CLIP-based models