Olive Recipes For AI Model Optimization Toolkit

This repository compliments Olive, the AI model optimization toolkit, and includes recipes demonstrating its extensive features and use cases. Users of Olive can use these recipes as a reference to either optimize publicly available AI models or to optimize their own proprietary models.

Supported models, architectures, devices and execution providers

Below are list of available recipes grouped by different criteria. Click the link to expand.

Models grouped by model architecture

bert	clip	deepseek	gemma	hiera	llama	llama3	mistral	mobilenet	phi3	phi4	qwen2	resnet	sam	sd	vit	whisper
google-bert-bert-base-multilingual-cased	OFA-Sys-chinese-clip-vit-base-patch16	deepseek-ai-DeepSeek-R1-Distill-Llama-8B	google-gemma-3-1b-it	sam2.1-hiera-small	deepseek-ai-DeepSeek-R1-Distill-Llama-8B	meta-llama-Llama-3.1-8B-Instruct	mistralai-Mistral-7B-Instruct-v0.2	timm-mobilenetv3_small_100.lamb_in1k	microsoft-Phi-3-mini-128k-instruct	microsoft-Phi-4-mini-instruct	Qwen-Qwen2.5-0.5B-Instruct	microsoft-resnet-50	sam-vit-base	sd-legacy-stable-diffusion-v1-5	google-vit-base-patch16-224	openai-whisper-large-v3-turbo
google-bert-bert-base-multilingual-cased	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	google-gemma-4-E2B-it		meta-llama-Llama-3.1-8B-Instruct	meta-llama-Llama-3.2-1B-Instruct	mistralai-Mistral-7B-Instruct-v0.2		microsoft-Phi-3-mini-128k-instruct	microsoft-Phi-4-mini-instruct	Qwen-Qwen2.5-0.5B-Instruct		sam2.1-hiera-small	sd2-community-stable-diffusion-2-1	google-vit-base-patch16-224	openai-whisper-large-v3-turbo
intel-bert-base-uncased-mrpc	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B			meta-llama-Llama-3.2-1B-Instruct	meta-llama-Llama-3.2-1B-Instruct	mistralai-Mistral-7B-Instruct-v0.3		microsoft-Phi-3-mini-128k-instruct	microsoft-Phi-4-mini-instruct	Qwen-Qwen2.5-0.5B		sam2.1-hiera-small		google-vit-base-patch16-224	openai-whisper-large-v3-turbo
intel-bert-base-uncased-mrpc	openai-clip-vit-base-patch16	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B				meta-llama-Llama-3.2-1B-Instruct			microsoft-Phi-3-mini-4k-instruct	microsoft-Phi-4-mini-reasoning	Qwen-Qwen2.5-1.5B-Instruct				sam-vit-base
	openai-clip-vit-base-patch16	deepseek-ai-DeepSeek-R1-Distill-Qwen-14B				meta-llama-Meta-Llama-3-8B			microsoft-Phi-3-mini-4k-instruct	microsoft-Phi-4-reasoning-plus	Qwen-Qwen2.5-1.5B-Instruct
	openai-clip-vit-base-patch32	deepseek-ai-DeepSeek-R1-Distill-Qwen-7B							microsoft-Phi-3-mini-4k-instruct	microsoft-Phi-4-reasoning	Qwen-Qwen2.5-1.5B-Instruct
	openai-clip-vit-base-patch32								microsoft-Phi-3.5-mini-instruct	microsoft-Phi-4	Qwen-Qwen2.5-1.5B-Instruct
	openai-clip-vit-large-patch14								microsoft-Phi-3.5-mini-instruct	microsoft-Phi-4	Qwen-Qwen2.5-14B-Instruct
									microsoft-Phi-3.5-mini-instruct		Qwen-Qwen2.5-14B-Instruct
									microsoft-Phi-3.5-mini-instruct		Qwen-Qwen2.5-3B-Instruct
									microsoft-Phi-4		Qwen-Qwen2.5-7B-Instruct
											Qwen-Qwen2.5-7B-Instruct
											Qwen-Qwen2.5-Coder-0.5B-Instruct
											Qwen-Qwen2.5-Coder-0.5B-Instruct
											Qwen-Qwen2.5-Coder-1.5B-Instruct
											Qwen-Qwen2.5-Coder-1.5B-Instruct
											Qwen-Qwen2.5-Coder-14B-Instruct
											Qwen-Qwen2.5-Coder-14B-Instruct
											Qwen-Qwen2.5-Coder-3B-Instruct
											Qwen-Qwen2.5-Coder-7B-Instruct
											Qwen-Qwen2.5-Coder-7B-Instruct
											deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B
											deepseek-ai-DeepSeek-R1-Distill-Qwen-14B
											deepseek-ai-DeepSeek-R1-Distill-Qwen-7B

Models grouped by device

cpu	gpu	npu
OFA-Sys-chinese-clip-vit-base-patch16	DeepSeek-R1-Distill-Llama-8B_Model_Builder_INT4	OFA-Sys-chinese-clip-vit-base-patch16
Qwen-Qwen2.5-0.5B-Instruct	DeepSeek-R1-Distill-Qwen-1.5B_Model_Builder_FP16	Qwen-Qwen2.5-0.5B-Instruct
Qwen-Qwen2.5-0.5B	DeepSeek-R1-Distill-Qwen-14B_NVMO_INT4_AWQ	Qwen-Qwen2.5-0.5B-Instruct
Qwen-Qwen2.5-1.5B-Instruct	DeepSeek-R1-Distill-Qwen-7B_NVMO_INT4_RTN	Qwen-Qwen2.5-1.5B-Instruct
Qwen-Qwen2.5-14B-Instruct	Llama-3.2-1B-Instruct_Model_Builder_FP16	Qwen-Qwen2.5-1.5B-Instruct
Qwen-Qwen2.5-3B-Instruct	Llama3.1-8B-Instruct_Model_Builder_INT4	Qwen-Qwen2.5-1.5B-Instruct
Qwen-Qwen2.5-7B-Instruct	Mistral-7B-Instruct-v0.2_Model_Builder_INT4	Qwen-Qwen2.5-1.5B-Instruct
Qwen-Qwen2.5-Coder-0.5B-Instruct	OFA-Sys-chinese-clip-vit-base-patch16	Qwen-Qwen2.5-14B-Instruct
Qwen-Qwen2.5-Coder-1.5B-Instruct	Phi-3-mini-128k-instruct_NVMO_INT4_RTN	Qwen-Qwen2.5-3B-Instruct
Qwen-Qwen2.5-Coder-14B-Instruct	Phi-3-mini-4k-instruct_Model_Builder_INT4	Qwen-Qwen2.5-7B-Instruct
Qwen-Qwen2.5-Coder-3B-Instruct	Phi3.5_Mini_Instruct_Model_Builder_INT4	Qwen-Qwen2.5-7B-Instruct
Qwen-Qwen2.5-Coder-7B-Instruct	Qwen-Qwen2.5-0.5B-Instruct	Qwen-Qwen2.5-7B-Instruct
alibaba-nlp-gte-large-en-v1.5	Qwen-Qwen2.5-0.5B-Instruct	Qwen-Qwen2.5-Coder-0.5B-Instruct
deepseek-ai-DeepSeek-R1-Distill-Llama-8B	Qwen-Qwen2.5-0.5B	Qwen-Qwen2.5-Coder-0.5B-Instruct
deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	Qwen-Qwen2.5-1.5B-Instruct-mixed	Qwen-Qwen2.5-Coder-1.5B-Instruct
deepseek-ai-DeepSeek-R1-Distill-Qwen-14B	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-Coder-1.5B-Instruct
deepseek-ai-DeepSeek-R1-Distill-Qwen-7B	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-Coder-14B-Instruct
facebook-opt-125m-splicegpt	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-Coder-3B-Instruct
gemma-3-1b-it_model_builder_cpu_FP32	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-Coder-7B-Instruct
gemma4-e2b-fp32-cpu	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-Coder-7B-Instruct
gemma4-e2b-int4-kquant-cpu	Qwen-Qwen2.5-1.5B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Llama-8B
google-bert-bert-base-multilingual-cased	Qwen-Qwen2.5-14B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B
google-gemma	Qwen-Qwen2.5-14B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B
google-vit-base-patch16-224	Qwen-Qwen2.5-3B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B
gpt-oss-20b	Qwen-Qwen2.5-7B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-14B
intel-bert-base-uncased-mrpc (ov)	Qwen-Qwen2.5-7B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-7B
intel-bert-base-uncased-mrpc-inc-smooth-quant	Qwen-Qwen2.5-Coder-0.5B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-7B
intel-bert-base-uncased-mrpc-ptq	Qwen-Qwen2.5-Coder-0.5B-Instruct	google-bert-bert-base-multilingual-cased
laion-CLIP-ViT-B-32-laion2B-s34B-b79K	Qwen-Qwen2.5-Coder-1.5B-Instruct	google-bert-bert-base-multilingual-cased
meta-llama-Llama-3.1-8B-Instruct	Qwen-Qwen2.5-Coder-1.5B-Instruct	google-bert-bert-base-multilingual-cased
meta-llama-Llama-3.2-1B-Instruct-dora	Qwen-Qwen2.5-Coder-14B-Instruct	google-gemma-3-1b-it
meta-llama-Llama-3.2-1B-Instruct-hqq	Qwen-Qwen2.5-Coder-14B-Instruct	google-vit-base-patch16-224
meta-llama-Llama-3.2-1B-Instruct-lmeval-onnx	Qwen-Qwen2.5-Coder-3B-Instruct	google-vit-base-patch16-224
meta-llama-Llama-3.2-1B-Instruct-lmeval	Qwen-Qwen2.5-Coder-7B-Instruct	google-vit-base-patch16-224
meta-llama-Llama-3.2-1B-Instruct-loha	Qwen-Qwen2.5-Coder-7B-Instruct	google-vit-base-patch16-224
meta-llama-Llama-3.2-1B-Instruct-lokr	Qwen2.5-0.5B-Instruct_Model_Builder_FP16	google-vit-base-patch16-224
meta-llama-Llama-3.2-1B-Instruct-mixed	Qwen2.5-14B-Instruct_Model_Builder_INT4	intel-bert-base-uncased-mrpc (AMD)
meta-llama-Llama-3.2-1B-Instruct-qlora	Qwen2.5-7B-Instruct_Model_Builder_INT4	intel-bert-base-uncased-mrpc (ov)
meta-llama-Llama-3.2-1B-Instruct	Qwen2.5-Coder-0.5B-Instruct_Model_Builder_FP16	intel-bert-base-uncased-mrpc
meta-llama-Meta-Llama-3-8B	Qwen2.5-Coder-1.5B-Instruct_Model_Builder_FP16	laion-CLIP-ViT-B-32-laion2B-s34B-b79K
microsoft-Phi-3-mini-128k-instruct	Qwen2.5-Coder-14B-Instruct_Model_Builder_INT4	laion-CLIP-ViT-B-32-laion2B-s34B-b79K
microsoft-Phi-3-mini-4k-instruct	Qwen2.5-Coder-7B-Instruct_Model_Builder_INT4	laion-CLIP-ViT-B-32-laion2B-s34B-b79K
microsoft-Phi-3.5-mini-instruct	Qwen2.5_1.5B_Instruct_Model_Builder_FP16	llama3.1-8b-instruct-x-elite
microsoft-Phi-4-mini-instruct	deepseek-ai-DeepSeek-R1-Distill-Llama-8B	llama3.1-8b-instruct-x2-elite
microsoft-Phi-4-mini-reasoning	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	meta-llama-Llama-3.1-8B-Instruct
microsoft-Phi-4	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	meta-llama-Llama-3.1-8B-Instruct
microsoft-deberta-base-mnli	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	meta-llama-Llama-3.1-8B-Instruct
microsoft-resnet-50	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	meta-llama-Llama-3.2-1B-Instruct
ministral_3_3b	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	meta-llama-Llama-3.2-1B-Instruct
mistralai-Mistral-7B-Instruct-v0.2	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	meta-llama-Llama-3.2-1B-Instruct
mistralai-Mistral-7B-Instruct-v0.3	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	microsoft-Phi-3-mini-128k-instruct
moonshine-tiny	deepseek-ai-DeepSeek-R1-Distill-Qwen-14B	microsoft-Phi-3-mini-128k-instruct
openai-clip-vit-base-patch16	deepseek-ai-DeepSeek-R1-Distill-Qwen-14B	microsoft-Phi-3-mini-128k-instruct
openai-clip-vit-base-patch32	deepseek-ai-DeepSeek-R1-Distill-Qwen-7B	microsoft-Phi-3-mini-128k-instruct
openai-clip-vit-large-patch14	deepseek-ai-DeepSeek-R1-Distill-Qwen-7B	microsoft-Phi-3-mini-4k-instruct
openai-whisper-base-cpu-int8	facebook-opt-125m-splicegpt	microsoft-Phi-3-mini-4k-instruct
openai-whisper-base.en-cpu-int8	gemma4-e2b-fp16-cuda	microsoft-Phi-3-mini-4k-instruct
openai-whisper-large-cpu-int8	gemma4-e2b-int4-kquant-cuda	microsoft-Phi-3-mini-4k-instruct
openai-whisper-large-v2-cpu-int8	google-bert-bert-base-multilingual-cased	microsoft-Phi-3.5-mini-instruct
openai-whisper-large-v3-cpu-int8	google-bert-bert-base-multilingual-cased	microsoft-Phi-3.5-mini-instruct
openai-whisper-large-v3-turbo-cpu-int8	google-bert-bert-base-multilingual-cased	microsoft-Phi-3.5-mini-instruct
openai-whisper-large-v3-turbo	google-bert-bert-base-multilingual-cased	microsoft-Phi-3.5-mini-instruct
openai-whisper-large-v3-turbo	google-bert-bert-base-multilingual-cased	microsoft-Phi-3.5-mini-instruct
openai-whisper-large-v3-turbo	google-bert-bert-base-multilingual-cased	microsoft-Phi-4-mini-instruct
openai-whisper-large-v3-turbo	google-gemma-3-1b-it	microsoft-Phi-4-mini-instruct
openai-whisper-large-v3-turbo	google-gemma	microsoft-Phi-4-mini-instruct
openai-whisper-medium-cpu-int8	google-vit-base-patch16-224	microsoft-Phi-4-mini-instruct
openai-whisper-medium.en-cpu-int8	google-vit-base-patch16-224	microsoft-Phi-4-mini-reasoning
openai-whisper-small-cpu-int8	google-vit-base-patch16-224	microsoft-Phi-4-mini-reasoning
openai-whisper-small.en-cpu-int8	google-vit-base-patch16-224	microsoft-Phi-4-reasoning-plus
openai-whisper-tiny-cpu-int8	google-vit-base-patch16-224	microsoft-Phi-4-reasoning
openai-whisper-tiny.en-cpu-int8	google-vit-base-patch16-224	microsoft-Phi-4-reasoning
qwen2.5-vl-3B-Instruct	gpt-oss-20b	microsoft-Phi-4-reasoning
qwen3.5-0.8B-Instruct	intel-bert-base-uncased-mrpc (ov)	microsoft-Phi-4-reasoning
qwen3.5-2B	intel-bert-base-uncased-mrpc-inc-quant	microsoft-resnet-50
qwen3.5-35B-A3B-MoE	intel-bert-base-uncased-mrpc-ptq	microsoft-resnet-50
qwen3.5-4B	intel-bert-base-uncased-mrpc	microsoft-resnet-50
qwen3.5-9B	intel-bert-base-uncased-mrpc	microsoft-table-transformer-detection
qwen3vl-2B-Instruct	intel-bert-base-uncased-mrpc	mistralai-Mistral-7B-Instruct-v0.2
qwen3vl-4B-Instruct	intel-bert-base-uncased-mrpc	mistralai-Mistral-7B-Instruct-v0.2
qwen3vl-8B-Instruct	intel-bert-base-uncased-mrpc	openai-clip-vit-base-patch16
sam2.1-hiera-small	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-base-patch16
sam2.1-hiera-small	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-base-patch16
sam2.1-hiera-small	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-base-patch32
sd-legacy-stable-diffusion-v1-5	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-base-patch32
sd2-community-stable-diffusion-2-1	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-base-patch32
sshleifer-tiny-gpt2-sparsegpt	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-large-patch14
stable-diffusion-v1-4-safety-checker	meta-llama-Llama-3.1-8B-Instruct	openai-clip-vit-large-patch14
stable-diffusion-v1-4-text-encoder	meta-llama-Llama-3.1-8B-Instruct	openai-clip-vit-large-patch14
stable-diffusion-v1-4-unet	meta-llama-Llama-3.1-8B-Instruct	openai-whisper-large-v3-turbo
stable-diffusion-v1-4-vae-decoder	meta-llama-Llama-3.1-8B-Instruct	openai-whisper-large-v3-turbo
stable-diffusion-v1-4-vae-encoder	meta-llama-Llama-3.2-1B-Instruct-dora	openai-whisper-large-v3-turbo
stable-diffusion-v1-5-safety-checker	meta-llama-Llama-3.2-1B-Instruct-hqq	openai-whisper-large-v3-turbo
stable-diffusion-v1-5-text-encoder	meta-llama-Llama-3.2-1B-Instruct-lmeval-onnx	openai-whisper-large-v3-turbo
stable-diffusion-v1-5-unet	meta-llama-Llama-3.2-1B-Instruct-lmeval	openai-whisper-large-v3-turbo
stable-diffusion-v1-5-vae-decoder	meta-llama-Llama-3.2-1B-Instruct-loha	openai-whisper-large-v3-turbo
stable-diffusion-v1-5-vae-encoder	meta-llama-Llama-3.2-1B-Instruct-lokr	openai-whisper-large-v3-turbo
stable-diffusion-v1-5	meta-llama-Llama-3.2-1B-Instruct-mixed	openai-whisper-large-v3-turbo
stable-diffusion-xl-base-1.0	meta-llama-Llama-3.2-1B-Instruct-qlora	qwen2.5-7b-instruct
timm-mobilenetv3_small_100.lamb_in1k	meta-llama-Llama-3.2-1B-Instruct	sam-vit-base
translategemma-4b-it	meta-llama-Llama-3.2-1B-Instruct	sam-vit-base
videochat-flash-qwen2_5-7b-internvideo2-1b	meta-llama-Llama-3.2-1B-Instruct	sam-vit-base
	meta-llama-Llama-3.2-1B-Instruct	sam-vit-base
	meta-llama-Llama-3.2-1B-Instruct	sam-vit-base
	meta-llama-Llama-3.2-1B-Instruct	sam2.1-hiera-small
	microsoft-Phi-3-mini-128k-instruct	sam2.1-hiera-small
	microsoft-Phi-3-mini-128k-instruct	sam2.1-hiera-small
	microsoft-Phi-3-mini-4k-instruct	sam2.1-hiera-small
	microsoft-Phi-3-mini-4k-instruct	sam2.1-hiera-small
	microsoft-Phi-3.5-mini-instruct	sam2.1-hiera-small
	microsoft-Phi-3.5-mini-instruct	sd-legacy-stable-diffusion-v1-5
	microsoft-Phi-3.5-mini-instruct	sd-legacy-stable-diffusion-v1-5
	microsoft-Phi-3.5-mini-instruct	sd2-community-stable-diffusion-2-1
	microsoft-Phi-3.5-mini-instruct	sd2-community-stable-diffusion-2-1
	microsoft-Phi-3.5-mini-instruct	stable-diffusion-v1-4-safety-checker
	microsoft-Phi-3.5-mini-instruct	stable-diffusion-v1-4-text-encoder
	microsoft-Phi-4-mini-instruct-mixed-tied	stable-diffusion-v1-4-unet
	microsoft-Phi-4-mini-instruct-mixed	stable-diffusion-v1-4-vae-decoder
	microsoft-Phi-4-mini-instruct	stable-diffusion-v1-4-vae-encoder
	microsoft-Phi-4-mini-instruct	stable-diffusion-v1-5-safety-checker
	microsoft-Phi-4-mini-instruct	stable-diffusion-v1-5-text-encoder
	microsoft-Phi-4-mini-instruct	stable-diffusion-v1-5-unet
	microsoft-Phi-4-mini-instruct_nvmo_ptq_mixed_precision_awq_lite	stable-diffusion-v1-5-vae-decoder
	microsoft-Phi-4-mini-reasoning	stable-diffusion-v1-5-vae-encoder
	microsoft-Phi-4-mini-reasoning	stable-diffusion-v1-5
	microsoft-Phi-4-mini-reasoning	stable-diffusion-xl-base-1.0
	microsoft-Phi-4-reasoning-plus	timm-mobilenetv3_small_100.lamb_in1k
	microsoft-Phi-4-reasoning	timm-mobilenetv3_small_100.lamb_in1k
	microsoft-Phi-4
	microsoft-Phi-4
	microsoft-Phi-4
	microsoft-resnet-50
	microsoft-resnet-50
	microsoft-resnet-50
	microsoft-resnet-50
	microsoft-resnet-50
	ministral_3_3b
	mistral-7b
	mistral-7b
	mistral-7b
	mistralai-Mistral-7B-Instruct-v0.2
	mistralai-Mistral-7B-Instruct-v0.2
	mistralai-Mistral-7B-Instruct-v0.3
	moonshine-tiny
	openai-clip-vit-base-patch16
	openai-clip-vit-base-patch16
	openai-clip-vit-base-patch16
	openai-clip-vit-base-patch16
	openai-clip-vit-base-patch16
	openai-clip-vit-base-patch16
	openai-clip-vit-base-patch32
	openai-clip-vit-base-patch32
	openai-clip-vit-base-patch32
	openai-clip-vit-base-patch32
	openai-clip-vit-base-patch32
	openai-clip-vit-base-patch32
	openai-clip-vit-large-patch14
	openai-clip-vit-large-patch14
	openai-clip-vit-large-patch14
	openai-clip-vit-large-patch14
	openai-whisper-base-cuda-int8
	openai-whisper-base-webgpu-int8
	openai-whisper-base.en-cuda-int8
	openai-whisper-base.en-webgpu-int8
	openai-whisper-large-cuda-int8
	openai-whisper-large-v2-cuda-int8
	openai-whisper-large-v2-webgpu-int8
	openai-whisper-large-v3-cuda-int8
	openai-whisper-large-v3-turbo-cuda-int8
	openai-whisper-large-v3-turbo-webgpu-int8
	openai-whisper-large-v3-turbo
	openai-whisper-large-v3-webgpu-int8
	openai-whisper-large-webgpu-int8
	openai-whisper-medium-cuda-int8
	openai-whisper-medium-webgpu-int8
	openai-whisper-medium.en-cuda-int8
	openai-whisper-medium.en-webgpu-int8
	openai-whisper-small-cuda-int8
	openai-whisper-small-webgpu-int8
	openai-whisper-small.en-cuda-int8
	openai-whisper-small.en-webgpu-int8
	openai-whisper-tiny-cuda-int8
	openai-whisper-tiny-webgpu-int8
	openai-whisper-tiny.en-cuda-int8
	openai-whisper-tiny.en-webgpu-int8
	phi-4_Model_Builder_INT4
	qwen2.5-vl-3B-Instruct
	qwen3.5-0.8B-Instruct
	qwen3.5-27B
	qwen3.5-2B
	qwen3.5-4B
	qwen3.5-9B
	qwen3vl-2B-Instruct
	qwen3vl-4B-Instruct
	qwen3vl-8B-Instruct
	sam2.1-hiera-small
	sam2.1-hiera-small
	sam2.1-hiera-small
	sd-legacy-stable-diffusion-v1-5
	sd2-community-stable-diffusion-2-1
	sshleifer-tiny-gpt2-sparsegpt
	stable-diffusion-v1-4-safety-checker
	stable-diffusion-v1-4-text-encoder
	stable-diffusion-v1-4-unet
	stable-diffusion-v1-4-vae-decoder
	stable-diffusion-v1-4-vae-encoder
	stable-diffusion-v1-5
	stable-diffusion-xl-base-1.0

Models grouped by EP

CPU	CUDA	Dml	MIGraphX	NvTensorRTRTX	OpenVINO	QNN	VitisAI	WebGpu
alibaba-nlp-gte-large-en-v1.5	Qwen-Qwen2.5-1.5B-Instruct-mixed	Qwen-Qwen2.5-1.5B-Instruct	google-bert-bert-base-multilingual-cased	DeepSeek-R1-Distill-Llama-8B_Model_Builder_INT4	OFA-Sys-chinese-clip-vit-base-patch16	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-0.5B-Instruct	ministral_3_3b
facebook-opt-125m-splicegpt	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	google-vit-base-patch16-224	DeepSeek-R1-Distill-Qwen-1.5B_Model_Builder_FP16	Qwen-Qwen2.5-0.5B-Instruct	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-1.5B-Instruct	openai-whisper-base-webgpu-int8
gemma-3-1b-it_model_builder_cpu_FP32	facebook-opt-125m-splicegpt	google-bert-bert-base-multilingual-cased	intel-bert-base-uncased-mrpc	DeepSeek-R1-Distill-Qwen-14B_NVMO_INT4_AWQ	Qwen-Qwen2.5-0.5B-Instruct	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-7B-Instruct	openai-whisper-base.en-webgpu-int8
gemma4-e2b-fp32-cpu	gemma4-e2b-fp16-cuda	google-vit-base-patch16-224	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	DeepSeek-R1-Distill-Qwen-7B_NVMO_INT4_RTN	Qwen-Qwen2.5-0.5B	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-Coder-0.5B-Instruct	openai-whisper-large-v2-webgpu-int8
gemma4-e2b-int4-kquant-cpu	gemma4-e2b-int4-kquant-cuda	intel-bert-base-uncased-mrpc	microsoft-resnet-50	Llama-3.2-1B-Instruct_Model_Builder_FP16	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-Coder-1.5B-Instruct	openai-whisper-large-v3-turbo-webgpu-int8
google-gemma	google-gemma	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-base-patch16	Llama3.1-8B-Instruct_Model_Builder_INT4	Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-7B-Instruct	Qwen-Qwen2.5-Coder-7B-Instruct	openai-whisper-large-v3-webgpu-int8
gpt-oss-20b	gpt-oss-20b	meta-llama-Llama-3.1-8B-Instruct	openai-clip-vit-base-patch32	Mistral-7B-Instruct-v0.2_Model_Builder_INT4	Qwen-Qwen2.5-14B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	openai-whisper-large-webgpu-int8
intel-bert-base-uncased-mrpc-inc-smooth-quant	intel-bert-base-uncased-mrpc-inc-quant	meta-llama-Llama-3.2-1B-Instruct	openai-clip-vit-large-patch14	Phi-3-mini-128k-instruct_NVMO_INT4_RTN	Qwen-Qwen2.5-14B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	deepseek-ai-DeepSeek-R1-Distill-Qwen-7B	openai-whisper-medium-webgpu-int8
intel-bert-base-uncased-mrpc-ptq	intel-bert-base-uncased-mrpc-ptq	microsoft-Phi-3.5-mini-instruct		Phi-3-mini-4k-instruct_Model_Builder_INT4	Qwen-Qwen2.5-3B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	google-bert-bert-base-multilingual-cased	openai-whisper-medium.en-webgpu-int8
meta-llama-Llama-3.2-1B-Instruct-dora	meta-llama-Llama-3.2-1B-Instruct-dora	microsoft-resnet-50		Phi3.5_Mini_Instruct_Model_Builder_INT4	Qwen-Qwen2.5-3B-Instruct	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	google-vit-base-patch16-224	openai-whisper-small-webgpu-int8
meta-llama-Llama-3.2-1B-Instruct-hqq	meta-llama-Llama-3.2-1B-Instruct-hqq	openai-clip-vit-base-patch16		Qwen-Qwen2.5-0.5B-Instruct	Qwen-Qwen2.5-7B-Instruct	google-bert-bert-base-multilingual-cased	intel-bert-base-uncased-mrpc (AMD)	openai-whisper-small.en-webgpu-int8
meta-llama-Llama-3.2-1B-Instruct-lmeval-onnx	meta-llama-Llama-3.2-1B-Instruct-lmeval-onnx	openai-clip-vit-base-patch32		Qwen-Qwen2.5-1.5B-Instruct	Qwen-Qwen2.5-7B-Instruct	google-bert-bert-base-multilingual-cased	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-whisper-tiny-webgpu-int8
meta-llama-Llama-3.2-1B-Instruct-lmeval	meta-llama-Llama-3.2-1B-Instruct-lmeval	openai-clip-vit-large-patch14		Qwen-Qwen2.5-14B-Instruct	Qwen-Qwen2.5-Coder-0.5B-Instruct	google-bert-bert-base-multilingual-cased	meta-llama-Llama-3.1-8B-Instruct	openai-whisper-tiny.en-webgpu-int8
meta-llama-Llama-3.2-1B-Instruct-loha	meta-llama-Llama-3.2-1B-Instruct-loha			Qwen-Qwen2.5-7B-Instruct	Qwen-Qwen2.5-Coder-0.5B-Instruct	google-vit-base-patch16-224	meta-llama-Llama-3.2-1B-Instruct
meta-llama-Llama-3.2-1B-Instruct-lokr	meta-llama-Llama-3.2-1B-Instruct-lokr			Qwen-Qwen2.5-Coder-0.5B-Instruct	Qwen-Qwen2.5-Coder-1.5B-Instruct	google-vit-base-patch16-224	microsoft-Phi-3-mini-128k-instruct
meta-llama-Llama-3.2-1B-Instruct-mixed	meta-llama-Llama-3.2-1B-Instruct-mixed			Qwen-Qwen2.5-Coder-1.5B-Instruct	Qwen-Qwen2.5-Coder-1.5B-Instruct	google-vit-base-patch16-224	microsoft-Phi-3-mini-4k-instruct
meta-llama-Llama-3.2-1B-Instruct-qlora	meta-llama-Llama-3.2-1B-Instruct-qlora			Qwen-Qwen2.5-Coder-14B-Instruct	Qwen-Qwen2.5-Coder-14B-Instruct	google-vit-base-patch16-224	microsoft-Phi-3.5-mini-instruct
meta-llama-Meta-Llama-3-8B	microsoft-Phi-3.5-mini-instruct			Qwen-Qwen2.5-Coder-7B-Instruct	Qwen-Qwen2.5-Coder-14B-Instruct	intel-bert-base-uncased-mrpc	microsoft-Phi-4-mini-instruct
microsoft-deberta-base-mnli	microsoft-Phi-4-mini-instruct-mixed-tied			Qwen2.5-0.5B-Instruct_Model_Builder_FP16	Qwen-Qwen2.5-Coder-3B-Instruct	intel-bert-base-uncased-mrpc	microsoft-Phi-4-mini-reasoning
ministral_3_3b	microsoft-Phi-4-mini-instruct-mixed			Qwen2.5-14B-Instruct_Model_Builder_INT4	Qwen-Qwen2.5-Coder-3B-Instruct	intel-bert-base-uncased-mrpc	microsoft-resnet-50
moonshine-tiny	ministral_3_3b			Qwen2.5-7B-Instruct_Model_Builder_INT4	Qwen-Qwen2.5-Coder-7B-Instruct	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	mistralai-Mistral-7B-Instruct-v0.2
openai-whisper-base-cpu-int8	mistral-7b			Qwen2.5-Coder-0.5B-Instruct_Model_Builder_FP16	Qwen-Qwen2.5-Coder-7B-Instruct	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-base-patch16
openai-whisper-base.en-cpu-int8	mistral-7b			Qwen2.5-Coder-1.5B-Instruct_Model_Builder_FP16	deepseek-ai-DeepSeek-R1-Distill-Llama-8B	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	openai-clip-vit-base-patch32
openai-whisper-large-cpu-int8	mistral-7b			Qwen2.5-Coder-14B-Instruct_Model_Builder_INT4	deepseek-ai-DeepSeek-R1-Distill-Llama-8B	llama3.1-8b-instruct-x-elite	openai-clip-vit-large-patch14
openai-whisper-large-v2-cpu-int8	moonshine-tiny			Qwen2.5-Coder-7B-Instruct_Model_Builder_INT4	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	llama3.1-8b-instruct-x2-elite	stable-diffusion-v1-5-safety-checker
openai-whisper-large-v3-cpu-int8	openai-whisper-base-cuda-int8			Qwen2.5_1.5B_Instruct_Model_Builder_FP16	deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	meta-llama-Llama-3.1-8B-Instruct	stable-diffusion-v1-5-text-encoder
openai-whisper-large-v3-turbo-cpu-int8	openai-whisper-base.en-cuda-int8			deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B	deepseek-ai-DeepSeek-R1-Distill-Qwen-14B	meta-llama-Llama-3.1-8B-Instruct	stable-diffusion-v1-5-unet
openai-whisper-large-v3-turbo	openai-whisper-large-cuda-int8			deepseek-ai-DeepSeek-R1-Distill-Qwen-14B	deepseek-ai-DeepSeek-R1-Distill-Qwen-14B	meta-llama-Llama-3.2-1B-Instruct	stable-diffusion-v1-5-vae-decoder
openai-whisper-large-v3-turbo	openai-whisper-large-v2-cuda-int8			deepseek-ai-DeepSeek-R1-Distill-Qwen-7B	deepseek-ai-DeepSeek-R1-Distill-Qwen-7B	meta-llama-Llama-3.2-1B-Instruct	stable-diffusion-v1-5-vae-encoder
openai-whisper-large-v3-turbo	openai-whisper-large-v3-cuda-int8			google-bert-bert-base-multilingual-cased	deepseek-ai-DeepSeek-R1-Distill-Qwen-7B	meta-llama-Llama-3.2-1B-Instruct	timm-mobilenetv3_small_100.lamb_in1k
openai-whisper-large-v3-turbo	openai-whisper-large-v3-turbo-cuda-int8			google-vit-base-patch16-224	google-bert-bert-base-multilingual-cased	meta-llama-Llama-3.2-1B-Instruct
openai-whisper-medium-cpu-int8	openai-whisper-medium-cuda-int8			intel-bert-base-uncased-mrpc	google-gemma-3-1b-it	microsoft-Phi-3-mini-128k-instruct
openai-whisper-medium.en-cpu-int8	openai-whisper-medium.en-cuda-int8			laion-CLIP-ViT-B-32-laion2B-s34B-b79K	google-gemma-3-1b-it	microsoft-Phi-3-mini-128k-instruct
openai-whisper-small-cpu-int8	openai-whisper-small-cuda-int8			meta-llama-Llama-3.1-8B-Instruct	google-vit-base-patch16-224	microsoft-Phi-3-mini-4k-instruct
openai-whisper-small.en-cpu-int8	openai-whisper-small.en-cuda-int8			meta-llama-Llama-3.2-1B-Instruct	google-vit-base-patch16-224	microsoft-Phi-3-mini-4k-instruct
openai-whisper-tiny-cpu-int8	openai-whisper-tiny-cuda-int8			microsoft-Phi-3-mini-128k-instruct	intel-bert-base-uncased-mrpc (ov)	microsoft-Phi-3.5-mini-instruct
openai-whisper-tiny.en-cpu-int8	openai-whisper-tiny.en-cuda-int8			microsoft-Phi-3-mini-4k-instruct	laion-CLIP-ViT-B-32-laion2B-s34B-b79K	microsoft-Phi-3.5-mini-instruct
qwen2.5-vl-3B-Instruct	qwen2.5-vl-3B-Instruct			microsoft-Phi-3.5-mini-instruct	meta-llama-Llama-3.1-8B-Instruct	microsoft-Phi-3.5-mini-instruct
qwen3.5-0.8B-Instruct	qwen3.5-0.8B-Instruct			microsoft-Phi-4-mini-instruct	meta-llama-Llama-3.1-8B-Instruct	microsoft-Phi-3.5-mini-instruct
qwen3.5-2B	qwen3.5-27B			microsoft-Phi-4-mini-instruct_nvmo_ptq_mixed_precision_awq_lite	meta-llama-Llama-3.2-1B-Instruct	microsoft-Phi-3.5-mini-instruct
qwen3.5-35B-A3B-MoE	qwen3.5-2B			microsoft-Phi-4	meta-llama-Llama-3.2-1B-Instruct	microsoft-Phi-3.5-mini-instruct
qwen3.5-4B	qwen3.5-4B			microsoft-resnet-50	microsoft-Phi-3-mini-128k-instruct	microsoft-Phi-4-mini-instruct
qwen3.5-9B	qwen3.5-9B			mistralai-Mistral-7B-Instruct-v0.2	microsoft-Phi-3-mini-128k-instruct	microsoft-Phi-4-mini-instruct
qwen3vl-2B-Instruct	qwen3vl-2B-Instruct			openai-clip-vit-base-patch16	microsoft-Phi-3-mini-4k-instruct	microsoft-Phi-4-reasoning
qwen3vl-4B-Instruct	qwen3vl-4B-Instruct			openai-clip-vit-base-patch32	microsoft-Phi-3-mini-4k-instruct	microsoft-Phi-4-reasoning
qwen3vl-8B-Instruct	qwen3vl-8B-Instruct			openai-clip-vit-large-patch14	microsoft-Phi-3.5-mini-instruct	microsoft-Phi-4-reasoning
sshleifer-tiny-gpt2-sparsegpt	sshleifer-tiny-gpt2-sparsegpt			phi-4_Model_Builder_INT4	microsoft-Phi-3.5-mini-instruct	microsoft-resnet-50
stable-diffusion-v1-4-safety-checker	stable-diffusion-v1-4-safety-checker				microsoft-Phi-4-mini-instruct	microsoft-resnet-50
stable-diffusion-v1-4-text-encoder	stable-diffusion-v1-4-text-encoder				microsoft-Phi-4-mini-instruct	microsoft-table-transformer-detection
stable-diffusion-v1-4-unet	stable-diffusion-v1-4-unet				microsoft-Phi-4-mini-instruct	openai-clip-vit-base-patch16
stable-diffusion-v1-4-vae-decoder	stable-diffusion-v1-4-vae-decoder				microsoft-Phi-4-mini-instruct	openai-clip-vit-base-patch16
stable-diffusion-v1-4-vae-encoder	stable-diffusion-v1-4-vae-encoder				microsoft-Phi-4-mini-reasoning	openai-clip-vit-base-patch16
stable-diffusion-v1-5-safety-checker	stable-diffusion-v1-5				microsoft-Phi-4-mini-reasoning	openai-clip-vit-base-patch32
stable-diffusion-v1-5-text-encoder	stable-diffusion-xl-base-1.0				microsoft-Phi-4-mini-reasoning	openai-clip-vit-base-patch32
stable-diffusion-v1-5-unet					microsoft-Phi-4-mini-reasoning	openai-clip-vit-base-patch32
stable-diffusion-v1-5-vae-decoder					microsoft-Phi-4-reasoning-plus	openai-clip-vit-large-patch14
stable-diffusion-v1-5-vae-encoder					microsoft-Phi-4-reasoning-plus	openai-whisper-large-v3-turbo
stable-diffusion-v1-5					microsoft-Phi-4-reasoning	openai-whisper-large-v3-turbo
stable-diffusion-xl-base-1.0					microsoft-Phi-4-reasoning	openai-whisper-large-v3-turbo
timm-mobilenetv3_small_100.lamb_in1k					microsoft-Phi-4	openai-whisper-large-v3-turbo
translategemma-4b-it					microsoft-Phi-4	openai-whisper-large-v3-turbo
videochat-flash-qwen2_5-7b-internvideo2-1b					microsoft-resnet-50	openai-whisper-large-v3-turbo
					mistralai-Mistral-7B-Instruct-v0.2	openai-whisper-large-v3-turbo
					mistralai-Mistral-7B-Instruct-v0.2	qwen2.5-7b-instruct
					mistralai-Mistral-7B-Instruct-v0.3	sam-vit-base
					openai-clip-vit-base-patch16	sam-vit-base
					openai-clip-vit-base-patch32	sam-vit-base
					openai-clip-vit-large-patch14	sam-vit-base
					openai-whisper-large-v3-turbo	sam-vit-base
					openai-whisper-large-v3-turbo	sam2.1-hiera-small
					openai-whisper-large-v3-turbo	sam2.1-hiera-small
					sam2.1-hiera-small	sam2.1-hiera-small
					sam2.1-hiera-small	sd-legacy-stable-diffusion-v1-5
					sam2.1-hiera-small	sd2-community-stable-diffusion-2-1
					sd-legacy-stable-diffusion-v1-5	stable-diffusion-v1-4-safety-checker
					sd-legacy-stable-diffusion-v1-5	stable-diffusion-v1-4-text-encoder
					sd2-community-stable-diffusion-2-1	stable-diffusion-v1-4-unet
					sd2-community-stable-diffusion-2-1	stable-diffusion-v1-4-vae-decoder
					stable-diffusion-v1-4-safety-checker	stable-diffusion-v1-4-vae-encoder
					stable-diffusion-v1-4-text-encoder	stable-diffusion-v1-5
					stable-diffusion-v1-4-unet	stable-diffusion-xl-base-1.0
					stable-diffusion-v1-4-vae-decoder	timm-mobilenetv3_small_100.lamb_in1k
					stable-diffusion-v1-4-vae-encoder
					stable-diffusion-v1-5

Learn more

• Olive Github Repository
• Getting Started
• Olive Documentation

🤝 Contributions and Feedback

• We welcome contributions! Please read the contribution guidelines for more details on how to contribute to the Olive project.
• For feature requests or bug reports, file a GitHub Issue.
• For general discussion or questions, use GitHub Discussions.

⚖️ License

Copyright (c) Microsoft Corporation. All rights reserved.

Licensed under the MIT License.