Skip to content

Latest commit

 

History

History
47 lines (44 loc) · 20.4 KB

File metadata and controls

47 lines (44 loc) · 20.4 KB

Model List

LLM Models

Model Name Supported Runtimes
Deepseek R1 Distill Llama 8B Intel CPU, Intel GPU, Intel NPU
Deepseek R1 Distill Qwen 1.5B Qualcomm NPU, Qualcomm GPU, AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Deepseek R1 Distill Qwen 14B NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Deepseek R1 Distill Qwen 7B AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Llama 3.1 8B Instruct Qualcomm NPU, AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Llama 3.2 1B Instruct Qualcomm NPU, Qualcomm GPU, AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Mistral 7B Instruct V0.2 AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Mistral 7B Instruct V0.3 Intel CPU, Intel GPU
Phi 3 Mini 128K Instruct Qualcomm NPU, AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Phi 3 Mini 4K Instruct Qualcomm NPU, AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Phi 3.5 Mini Instruct Qualcomm NPU, Qualcomm GPU, AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Phi 4 NVIDIA TensorRT for RTX, Intel CPU, Intel GPU
Phi 4 Mini Instruct Qualcomm NPU, AMD NPU, Intel CPU, Intel GPU, Intel NPU
Phi 4 Mini Reasoning AMD NPU, Intel CPU, Intel GPU, Intel NPU
Phi 4 Reasoning Intel NPU
Phi 4 Reasoning Plus Intel NPU
Qwen2.5 0.5B Instruct AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Qwen2.5 1.5B Instruct Qualcomm NPU, Qualcomm GPU, AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Qwen2.5 14B Instruct NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Qwen2.5 3B Instruct Intel CPU, Intel GPU, Intel NPU
Qwen2.5 7B Instruct Qualcomm NPU, AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Qwen2.5 Coder 0.5B Instruct AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Qwen2.5 Coder 1.5B Instruct AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Qwen2.5 Coder 14B Instruct NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU
Qwen2.5 Coder 3B Instruct Intel CPU, Intel GPU, Intel NPU
Qwen2.5 Coder 7B Instruct AMD NPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU

Non-LLM Models

Model Name Supported Runtimes
Bert Base Multilingual Cased Qualcomm NPU, Qualcomm GPU, AMD NPU, AMD GPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Bert Base Uncased Mrpc Qualcomm NPU, Qualcomm GPU, AMD NPU, AMD GPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Chinese Clip Vit Base Patch16 Intel CPU, Intel GPU, Intel NPU
Clip Vit B 32 Laion2B S34B B79K Qualcomm NPU, Qualcomm GPU, AMD NPU, AMD GPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Clip Vit Base Patch16 Qualcomm NPU, Qualcomm GPU, AMD NPU, AMD GPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Clip Vit Base Patch32 Qualcomm NPU, Qualcomm GPU, AMD NPU, AMD GPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Clip Vit Large Patch14 Qualcomm NPU, AMD NPU, AMD GPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Resnet 50 Qualcomm NPU, Qualcomm GPU, AMD NPU, AMD GPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Stable Diffusion V1 5 Qualcomm NPU, Intel CPU, Intel GPU
Vit Base Patch16 224 Qualcomm NPU, Qualcomm GPU, AMD NPU, AMD GPU, NVIDIA TensorRT for RTX, Intel CPU, Intel GPU, Intel NPU, DirectML
Whisper Large V3 Turbo Qualcomm NPU