AI Chips
AI Chip GPUs
Data Center GPU/Accelerator Shipments
Quarterly shipments of AI accelerators: the specialized chips (GPUs, TPUs, custom ASICs) that train and run AI models in data centers. NVIDIA captures over 80% of unit volume; AMD, Intel, and Google's TPUs trail well behind. Figures in thousands of units.
AI Accelerator Architecture Comparison
Side-by-side comparison of AI training and inference accelerators: specs, memory, performance, and pricing
| Product | Architecture | Node | Transistors | Memory | Mem BW | FP16 TFLOPS | FP8 TFLOPS | TDP | Interconnect | Launched | Price Est. |
|---|---|---|---|---|---|---|---|---|---|---|---|
 H100 SXM | Hopper | 4nm (TSMC) | 80B | 80GB HBM3 | 3.35 TB/s | 1,979 | 3,958 | 700W | NVLink 4.0 (900 GB/s) | 2023-Q1 | $25,000–$40,000 |
| B200 | Blackwell | 4nm (TSMC) | 208B | 192GB HBM3E | 8 TB/s | 5,000 | 10,000 | 1000W | NVLink 5.0 (1.8 TB/s) | 2024-Q4 | $30,000–$50,000 |
| GB200 NVL72 | Blackwell | 4nm (TSMC) | 208B (x72) | 13.5TB HBM3E | 576 TB/s | 162K | 1440K | 120kW | NVLink 5.0 (full rack) | 2025-Q1 | $2M–$3M (rack) |
 MI300X | CDNA 3 | 5nm/6nm (TSMC) | 153B | 192GB HBM3 | 5.3 TB/s | 1,307 | 2,614 | 750W | Infinity Fabric (896 GB/s) | 2023-Q4 | $10,000–$15,000 |
| MI325X | CDNA 3.5 | 5nm/6nm (TSMC) | 153B | 256GB HBM3E | 6 TB/s | 1,307 | 2,614 | 750W | Infinity Fabric (896 GB/s) | 2024-Q4 | $15,000–$20,000 |
| MI350X | CDNA 4 | 3nm (TSMC) | 185B | 288GB HBM3E | 8 TB/s | 5,000 | 10,000 | 1000W | UALink / Infinity Fabric 4.0 | 2025-Q2 | TBD |
 Gaudi 2 | Gaudi | 7nm (TSMC) | ~25B | 96GB HBM2E | 2.46 TB/s | 432 | 864 | 600W | 24x 100GbE RDMA | 2023-Q2 | $12,000–$15,000 |
| Gaudi 3 | Gaudi | 5nm (TSMC) | ~50B | 128GB HBM2E | 3.7 TB/s | 1,835 | 3,670 | 900W | 24x 200GbE RDMA | 2024-Q4 | $15,000–$20,000 |
 Google TPU v5e | Custom ASIC | 7nm (TSMC) | ~20B | 16GB HBM2E | 820 GB/s | 197 | 394 | 200W | ICI (Inter-Chip Interconnect) | 2023-Q3 | Cloud-only |
| Google TPU v6e (Trillium) | Custom ASIC | 5nm (TSMC) | ~35B | 32GB HBM3 | 1.6 TB/s | 460 | 920 | 300W | ICI v2 | 2024-Q4 | Cloud-only |
AI Chip Product Roadmap
Product availability timeline for AI accelerators across NVIDIA, AMD, Intel, and Broadcom/Google
Legacy
In Production
Announced
Roadmap
2020
2021
2022
2023
2024
2025
2026
2027
2028
NVIDIAA100 (7nm)
H100 (4nm)
H200 (4nm)
B100/B200 (4nm)
GB200 NVL72 (4nm)
Rubin (R100) (3nm)
Feynman (2nm)
AMDMI250X (6nm)
MI300X (5nm)
MI325X (5nm)
MI350X (3nm)
MI400 (2nm)
IntelGaudi 2 (7nm)
Gaudi 3 (5nm)
Jaguar Shores (Intel 18A)
BroadcomGoogle TPU v5e (7nm)
Google TPU v6e (Trillium) (5nm)
Google TPU v7 (Ironwood) (5nm)
Meta MTIA v2 (5nm)
Data Center GPU + Accelerator Revenue by Vendor (Quarterly)
Quarterly data center AI accelerator revenue by vendor (NVDA, AMD, INTC, AVGO). NVDA holds roughly 85% share.
NVIDIA Data Center Compute vs Networking
NVIDIA-disclosed Data Center compute versus networking, only for fiscal quarters where both lines were printed. Networking (InfiniBand, Spectrum-X, NVLink fabric) was $14.8B in FY27 Q1, almost 20% of Data Center.
Hyperscaler Custom AI Accelerators
Company-stated custom accelerators (Google TPU, AWS Trainium, Azure Maia, Meta MTIA) plus Intel Foundry external customer revenue. This is a landscape table, not a shipment ranking. Foundry names appear only when the cited page states them.
| Product | Owner | What the owner has said | Foundry (only if disclosed) |
|---|---|---|---|
| TPU Ironwood (7th gen) | Google Cloud describes Ironwood as the 7th-generation TPU, built for inference and training at Gemini scale, available on Google Cloud | Not stated on the cited Cloud blog; TSMC is widely assumed and is not treated as a Google disclosure here | |
| Trainium2 / Trn2 | Amazon Web Services | AWS documents Trainium2 as the current-generation training chip for Amazon EC2 Trn2 instances and UltraServers, sold as an NVIDIA alternative for AWS-hosted training | Not stated on the cited AWS product page |
| Azure Maia | Microsoft | Microsoft describes Azure Maia as an in-house AI accelerator for Azure OpenAI and internal training and inference. Maia 100 is the first generation discussed on the Azure blog | Maia 3 on Intel 18A is reported by Intel/Microsoft coverage; the cited Azure Maia blog does not name a foundry for Maia 100 |
| MTIA | Meta | Meta's engineering blog describes MTIA as a family of training and inference accelerators for ranking and recommendation, now in production inside Meta data centers | Meta has publicly worked with Broadcom on custom silicon; the cited MTIA blog is about the chip, not a foundry share figure |
| Intel Foundry external AI silicon | Intel Foundry customers | Intel's Q2 2026 10-Q: third-party foundry and assembly/test revenue was $293 million in the quarter (vs $22 million a year earlier). That is the disclosed external foundry print, not a named list of AI chips | Intel Foundry |
Prefer Sterling in Google
Add sterlingcharts.com as a preferred source so our charts can appear with a preferred badge in Google Top Stories, AI Mode, and AI Overviews.