• Lecture

AI Hardwares

AI chips

Nvidia

NVIDIA GTC 2026 Maps Out a New Blueprint: Rubin, Feynman, and CPO Emerge as Three Key Pillars

Vera Rubin

Groq-3 LPU

DGX-Spark

RTX Spark

Geforce RTX 50 series

AMD Ryzen

Google TPU-8

TPU 8t ASIC block diagram

TPU 8i ASIC block diagram

AWS Neuron

Inferential2

Trainium3

Tesla

AI-6

AI-5

特斯拉 AI5 / HW5 下代 FSD 晶片號稱運算性能達 2,000~2,500TOPS（每秒兆次操作），是現款 HW4（約 500TOPS）晶片五倍，可支援更複雜的無監督 FSD 演算法。輝達 RTX5080 和 RTX5090（分別約為 1,500 美元和 3,000 美元）運算性能為 1,800TOPS 和 3,400TOPS。

Tesla’s Hardware & E/E Architecture

Tesla’s lane prediction model architecture

Edge AI

Nvidia Jetson

  Jetson AGX Thor(T5000) Jetson AGX Orin 64GB Jetson Orin NX 16GB Jetson Orin Nano Super Jetson AGX Xavier Jetson Xavier NX Jetson Nano
AI Performance 2070 TFLOPS 275 TOPS 100 TOPS 67 TOPS 32 TOPS 21 TOPS 472 GFLOPS
GPU 2560-core NVIDIA Blackwell architecture GPU with 96 Tensor Cores 2048-core NVIDIA Ampere architecture GPU with 64 Tensor Cores 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores 512-core NVIDIA Volta architecture GPU with 64 Tensor Cores 384-core NVIDIA Volta™ architecture GPU with 48 Tensor Cores 128-core NVIDIA Maxwell™ architecture GPU
GPU Max Frequency 1.57 GHz 1.3 GHz 918 MHz 1020 MHz 1377 MHz 1100 MHz 921MHz
CPU 14-core Arm® Neoverse®-V3AE 64-bit CPU 1MB L2 + 16MB L3 12-core NVIDIA Arm® Cortex A78AE v8.2 64-bit CPU 3MB L2 + 6MB L3 8-core NVIDIA Arm® Cortex A78AE v8.2 64-bit CPU 2MB L2 + 4MB L3 6-core Arm® Cortex®-A78AE v8.2 64-bit CPU 1.5MB L2 + 4MB L3 8-core NVIDIA Carmel Arm®v8.2 64-bit CPU 8MB L2 + 4MB L3 6-core NVIDIA Carmel Arm®v8.2 64-bit CPU 6MB L2 + 4MB L3 Quad-Core Arm® Cortex®-A57 MPCore processor
CPU Max Frequency 2.6 GHz 2.2 GHz 2.0 GHz 1.7 GHz 2.2 GHz 1.9 GHz 1.43GHz
Memory 128GB 256-bit LPDDR5X 273GB/s 64GB 256-bit LPDDR5 204.8GB/s 16GB 128-bit LPDDR5 102.4GB/s 8GB 128-bit LPDDR5 102 GB/s 32GB 256-bit LPDDR4x 136.5GB/s 8GB 128-bit LPDDR4x 59.7GB/s 4GB 64-bit LPDDR4 25.6GB/s

Jetson Thor

Introducing NVIDIA Jetson Thor, the Ultimate Platform for Physical AI

NVIDIA® Jetson Orin Nano™ Super 入門套件包

樹莓派 RPi-5


  • Broadcom BCM2712 2.4GHz quad-core 64-bit ARM Cortex-A76 CPU, with Cryptographic Extension, 512KB per-core L2 caches, and a 2MB shared L3 cache
  • Hailo-8L HAT (13 TOPs)

耐能 Kneron KL730 AI Soc

  • Quad ARM® Cortex™ A55 CPU, 高達3.6eTOPS@int8 / 7.2eTops@int4
  • 內建DSP，可以加速AI模型後處理，語音處理

堪智 Kendryte K230

  • 1.6GHz & 0.8GHz Dual-core 64-bit RISC-V (6 TOPs), VPU: H.264/H.265
  • 1/2GB 32-bit LPDDR4/DDR4/LPDDR3/DDR3, SD3.01, eMMC 5.0

STMicro STM32N6 series

  • Cortext-M55 800MHz, Neural-ART (0.6TOPs / 3TOPs), 4.2MB Flash, H.264, JPEG

Infineon PSOC Edge

  • Cortex-M55 + Helium DSP @500MHz, Cortex-M33 @200MHz, NNLite + Ethos™ U55-128 (4 TOPS), SRAM up to 5/6MB

Realtek AMB82-mini


  • RTL8735B: 32-bit ARM v8M, @500MHz, 768KB ROM, 512KB RAM, 16MB Flash, DDR2/DDR3L up to 128MB, NN Engine (0.4 TOPs)
  • 802.11 a/b/g/n Wi-Fi 2.4GHz/5GHz, BLE 5.1

Agent Harewares comparison

Feature Pi-5 Mini PC (N100) Jetson-Super-Nano Mac-Mini M4
Price ~€95 ~€200 €399 €650+
RAM 8GB 16GB 8GB 16-24GB (unified)
AI Engine None CPU-only 67 TOPS GPU ~38 TOPS Neural Engine
Power 5-10W 15-35W 15W 10-25W
Noise Silent Varies (fan) Silent (fanless) Near-silent
Local LLM ❌ Barely ✅ (quantized) ✅ (up to 13B)
Storage SD/NVMe HAT NVMe 512GB NVMe 256GB-2TB



This site was last updated June 19, 2026.

  • basic