AI accelerator Neural Processing Unit NPU, Digital signal processor DSP trillion operations per second
Apple A11 iPhone 8/8 Plus/X, Neural Engine, 600 GOPS
Apple A12 iPhone XS/XR/iPad 8/iPad Air 3/A12X iPad Pro 3 ce/A12Z iPad Pro 4, Next-generation Neural Engine, 8 cores, 5 TOPS
Apple A13 iPhone 11/iPad 9 ks, 8-core, 6 TOPS
Apple A14 iPhone 12/iPad 10 hl/iPad Air 4 kh, 4-6 GB, 16-core, 11 TOPS
Apple M1 iPad Air 5/iPad Pro 5 ca, 8- GB, 16-core, 11 TOPS
Apple A15 iPhone 13/13 Pro/14 kh, 4-6GB, 16-core, 15.8 TOPS
Apple M2 iPad Air 6 2024/iPad Pro 6, 8- GB, 16-core, 15.8 TOPS
Apple A16 iPhone 14 Pro/15 ca, 6 GB, 16-core, 17 TOPS
Apple A17 Pro iPhone 15 Pro, 8 GB, 16-core, 35 TOPS
Apple M3 Mac 8 GB, 16-core, 18 TOPS
Apple M4 iPad Pro 7, 8 GB, 38 TOPS
Apple A18 Pro iPhone 16, 35 TOPS
Qualcomm Snapdragon systems on chips: Snapdragon_8/8s Gen 3 (2024)
Google Tensor with Tensor Processing Unit (Edge_TPU) used in Pixel Phones
A guide to AI TOPS and NPU performance metrics
* Qualcomm Snapdragon X series Elite/Plus DSP 45 TOPS, GPU 3.8-4.6 TFLOPS
* AMD Ryzen AI 9 HX Series 300, Ryzen AI 300 series, 365/370 28W (15-54W) 50 TOPS, 375 55 TOPS,
* Intel Core Ultra 200V Series Intel Core Ultra 7 17W (8-37W): 256V 16GB, 258V 32GB 47 TOPS, 266V 16GB, 268V 32GB 48 TOPS
Intel AMX XMX Advanced Matrix Extensions in CPU, Xe Matrix Extensions in GPU
Microsoft Copilot+ PC 40 TOPS, 16 GB memory, 256 GB storage
Apple Intelligence ChatGPT-4o Code Completion 16GB
Best chatbot ChatGPT alternatives Anthropic Claude, Google Gemini for live data, Microsoft Copilot creative, Perplexity research, Inflection Pi personal, xAI Grok social, Llama open source, MetaAI fun, Poe more choices comparison
