The Silicon Zoo
Vetted Specifications for AI Accelerators and Edge Devices
The Silicon Zoo is the authoritative registry for physical hardware in mlsysim. Every specification is typed (pint.Quantity), provenance-tracked, and validated against official datasheets and MLPerf baselines—so you never have to argue about what the A100’s bandwidth actually is.
Reference these specs when reasoning about bottlenecks. For any device listed here, you can load it directly in Python: hw = mlsysim.Hardware.Cloud.A100. The three columns that matter most for roofline analysis are Peak Performance, Memory BW, and Capacity.
Data Center Accelerators
| Device | Year | Peak Performance | Memory BW | Capacity | TDP |
|---|---|---|---|---|---|
| NVIDIA B200 | 2024 | 2.2 PFLOPs/s | 8.0 TB/s | 206.2 GB | 1,000 W |
| Cerebras CS-3 (WSE-3) | 2024 | 125.0 PFLOPs/s | 21.0 PB/s | 44.0 GB | 23,000 W |
| NVIDIA GB200 NVL72 | 2024 | 162.0 PFLOPs/s | 576.0 TB/s | 13.8 TB | 120 kW |
| Intel Gaudi 3 | 2024 | 1.8 PFLOPs/s | 3.7 TB/s | 137.4 GB | 900 W |
| Reference Desktop CPU | 2024 | 1.0 TFLOPs/s | 50.0 GB/s | 68.7 GB | 150 W |
| Google TPU v6 (Trillium) | 2024 | 918.0 TFLOPs/s | 1,600.0 GB/s | 34.4 GB | 300 W |
| AWS Trainium 2 | 2024 | 380.0 TFLOPs/s | 2.4 TB/s | 103.1 GB | 500 W |
| NVIDIA H200 | 2023 | 989.0 TFLOPs/s | 4.8 TB/s | 140.7 GB | 700 W |
| AMD MI300X | 2023 | 1.3 PFLOPs/s | 5.3 TB/s | 206.2 GB | 750 W |
| Google TPU v5p | 2023 | 459.0 TFLOPs/s | 2.8 TB/s | 102.0 GB | 300 W |
| Intel Gaudi 2 | 2022 | 432.0 TFLOPs/s | 2.5 TB/s | 103.1 GB | 600 W |
| NVIDIA H100 | 2022 | 989.0 TFLOPs/s | 3.4 TB/s | 85.9 GB | 700 W |
| AMD MI250X | 2021 | 383.0 TFLOPs/s | 3.2 TB/s | 137.4 GB | 500 W |
| Google TPU v4 | 2021 | 275.0 TFLOPs/s | 1,200.0 GB/s | 34.4 GB | 200 W |
| NVIDIA A100 | 2020 | 312.0 TFLOPs/s | 2,039.0 GB/s | 85.9 GB | 400 W |
| Intel SGX Enclave (Reference) | 2020 | 1.0 TFLOPs/s | 10.0 GB/s | 128.0 MB | — |
| Google TPU v3 | 2019 | 105.0 TFLOPs/s | 900.0 GB/s | 34.4 GB | 250 W |
| NVIDIA T4 | 2018 | 65.0 TFLOPs/s | 320.0 GB/s | 17.2 GB | 70 W |
| Google TPU v2 | 2018 | 45.0 TFLOPs/s | 700.0 GB/s | 17.2 GB | 200 W |
| Google TPU v1 | 2017 | 92.0 TFLOPs/s | 34.0 GB/s | 8.6 GB | 75 W |
| NVIDIA V100 | 2017 | 125.0 TFLOPs/s | 900.0 GB/s | 34.4 GB | 300 W |
| NVIDIA V100 PCIe | 2017 | 112.0 TFLOPs/s | 900.0 GB/s | 34.4 GB | 250 W |
Workstations
| Device | Year | Peak Performance | Memory BW | Capacity | TDP |
|---|---|---|---|---|---|
| NVIDIA DGX Spark (GB10) | 2025 | 125.0 TFLOPs/s | 273.0 GB/s | 128.0 GB | 200 W |
| MacBook Pro (M3 Max) | 2023 | 14.2 TFLOPs/s | 400.0 GB/s | 128.0 GB | 100 W |
Mobile Devices
| Device | Year | Peak Performance | Memory BW | Capacity | TDP |
|---|---|---|---|---|---|
| Google Pixel 8 (Tensor G3) | 2023 | 15.0 TFLOPs/s | 60.0 GB/s | 8.0 GB | 5 W |
| Snapdragon 8 Gen 3 | 2023 | 45.0 TFLOPs/s | 77.0 GB/s | 12.0 GB | 5 W |
| iPhone 15 Pro (A17 Pro) | 2023 | 35.0 TFLOPs/s | 100.0 GB/s | 8.0 GB | 5 W |
| Apple M2 Neural Engine | 2022 | 15.8 TFLOPs/s | 100.0 GB/s | 16.0 GB | 20 W |
Edge & Robotics
| Device | Year | Peak Performance | Memory BW | Capacity | TDP |
|---|---|---|---|---|---|
| Edge Server | 2024 | 1.0 TFLOPs/s | 100.0 GB/s | 128.0 GB | 300 W |
| NVIDIA Jetson Orin NX | 2023 | 25.0 TFLOPs/s | 102.0 GB/s | 16.0 GB | 25 W |
| NVIDIA Jetson Orin Nano | 2023 | 10.0 TFLOPs/s | 68.0 GB/s | 8.0 GB | 15 W |
| NVIDIA Jetson AGX Orin | 2022 | 275.0 TFLOPs/s | 204.0 GB/s | 64.0 GB | 60 W |
| RoboTaxi Reference Compute (NVIDIA DRIVE AGX Orin class) | 2022 | 5.2 TFLOPs/s | 200.0 GB/s | 32.0 GB | 60 W |
| Intel NUC + Movidius | 2020 | 1.0 TFLOPs/s | 25.0 GB/s | 16.0 GB | 15 W |
| Google Coral Edge TPU | 2019 | 4.0 TFLOPs/s | 8.0 GB/s | 1.0 GB | 2 W |
TinyML Microcontrollers
| Device | Year | Peak Performance | Memory BW | Capacity | TDP |
|---|---|---|---|---|---|
| Oura Ring 4 (wearable reference profile) | 2024 | 100.0 MFLOPs/s | 0.1 GB/s | 2.0 MB | 0 W |
| ESP32-S3 (AI) | 2022 | 500.0 MFLOPs/s | 0.1 GB/s | 4.0 MB | 0 W |
| Himax WE-I Plus | 2020 | 200.0 MFLOPs/s | 0.1 GB/s | 2.0 MB | 0 W |
| Nordic nRF52840 (Cortex-M4F) | 2018 | 64.0 MFLOPs/s | 0.1 GB/s | 1.0 MB | 0 W |
How to Read the Silicon Zoo
The Three Numbers That Matter
For roofline analysis, focus on three columns:
Peak Performance (TFLOP/s) — the compute ceiling. This determines how fast compute-bound workloads run (e.g., large-batch training, LLM pre-fill).
Memory Bandwidth (TB/s) — the memory ceiling. This determines how fast memory-bound workloads run (e.g., small-batch inference, LLM token decoding).
Capacity (GB) — the memory wall. If your model plus activations exceed this, the workload is infeasible on a single device.
The Ridge Point
The ratio of Peak Performance to Memory Bandwidth gives the ridge point (in FLOP/byte). Workloads with arithmetic intensity below the ridge point are memory-bound; above it, compute-bound. See the Math Foundations page for the full derivation.
Common Patterns
- Cloud GPUs (A100, H100, H200) have 40-80+ GB of HBM with very high bandwidth (2-5 TB/s). They are designed for throughput.
- Edge devices (Jetson) trade peak performance for lower power budgets, making TDP per TFLOP a useful comparison metric.
- TinyML MCUs (RP2040, nRF5340) have KB-scale memory — only the smallest quantized models fit. Use the Model Zoo to find matching workloads.
Textbook Connection
These specifications are used throughout Volumes 1 and 2 of the textbook. The Hardware Acceleration chapter uses them for roofline construction, and the Compute Infrastructure chapter uses them for fleet sizing and TCO analysis.
You can define custom hardware specs on-the-fly in Python or contribute new vetted specs to the registry. See the Contributing Guide for how to add persistent specs, or the Hardware API Reference for defining custom HardwareNode objects.
Browse the Silicon Zoo from your terminal: mlsysim zoo hardware
For full technical specs and validation details, see the API Reference.