Custom AI chips designed in-house
17 chips come from the owner's own design team: T-Head, Annapurna Labs, Kunlunxin, HiSilicon and Microsoft. Top stated FP8: Huawei Ascend 960 at 2,000 TFLOPS per chip. Largest fixed memory entry: Alibaba T-Head Zhenwu M890 with 144 GB. Largest pod: Huawei Ascend 960 at 15,488 chips.
| Alibaba T-Head Zhenwu 810E | Alibaba | In-house (T-Head) | — | 961 | 2.771 | — | — | — | — | — | — | — | — | — | Deployed | 2,0262 | 2026-11-11 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Alibaba T-Head Zhenwu M890 | Alibaba | In-house (T-Head) | — | 1441 | — | — | — | — | — | — | — | — | — | 1281 | Announced | 2,0261 | 2026-11-11 |
| AWS Graviton5 | Amazon Web Services | In-house (Annapurna Labs) | TSMC 3 nm | — | — | — | — | — | — | — | — | — | — | — | Deployed | 2,0251 | 2026-11-11 |
| Baidu Kunlunxin M100 | Baidu | In-house (Kunlunxin) | — | — | — | — | — | — | — | — | — | — | — | — | Announced | 2,0251 | 2026-11-11 |
| Baidu Kunlunxin M300 | Baidu | In-house (Kunlunxin) | — | — | — | — | — | — | — | — | — | — | — | — | Announced | 2,0251 | 2026-11-11 |
| Huawei Ascend 950DT | Huawei | In-house (HiSilicon) | — | 1441 | 41 | 1,0001 | — | — | — | — | 2,0001 | — | — | 8,1921 | Sampling | 2,0251 | 2026-11-11 |
| Huawei Ascend 950PR | Huawei | In-house (HiSilicon) | — | — | — | 1,0001 | — | — | — | — | 2,0001 | — | — | — | Deployed | 2,0251 | 2026-11-11 |
| Huawei Ascend 960 | Huawei | In-house (HiSilicon) | — | — | — | 2,0001 | — | — | — | — | 4,0001 | — | — | 15,4881 | Announced | 2,0251 | 2026-11-11 |
| Huawei Ascend 910C | Huawei | In-house (HiSilicon) | SMIC N+2 (7 nm-class) | 1281 | 3.21 | — | — | — | 7521 | — | — | — | — | 3841 | Deployed | 2,0244 | 2026-11-11 |
| AWS Graviton4 | Amazon Web Services | In-house (Annapurna Labs) | — | — | — | — | — | — | — | — | — | — | — | — | Deployed | 2,0231 | 2026-11-11 |
| AWS Trainium2 | Amazon Web Services | In-house (Annapurna Labs) | — | 961 | 2.91 | 1,2991 | — | — | 6671 | — | — | — | — | 642 | Deployed | 2,0234 | 2026-11-11 |
| Microsoft Cobalt 100 | Microsoft | In-house | — | — | — | — | — | — | — | — | — | — | — | — | Deployed | 2,0231 | 2026-11-11 |
| AWS Inferentia2 | Amazon Web Services | In-house (Annapurna Labs) | — | 321 | 0.881 | — | — | — | 1901 | — | — | — | — | — | Deployed | 2,0223 | 2026-11-11 |
| Huawei Ascend 910B | Huawei | In-house (HiSilicon) | SMIC 7 nm (N+2) | 641 | 1.62 | — | — | — | — | 4001 | — | — | — | — | Deployed | 2,0222 | 2026-11-11 |
| AWS Trainium | Amazon Web Services | In-house (Annapurna Labs) | — | 321 | 0.821 | — | — | — | 1901 | — | — | — | — | 161 | Deployed | 2,0203 | 2026-11-11 |
| AWS Inferentia | Amazon Web Services | In-house (Annapurna Labs) | — | 81 | 0.051 | — | — | — | 641 | — | — | — | — | 162 | Deployed | 2,0183 | 2026-11-11 |
| Baidu Kunlunxin P800 | Baidu | In-house (Kunlunxin) | — | 961 | — | — | — | — | — | 3451 | — | — | — | 2563 | Deployed | — | 2026-11-11 |
Every chip in this list
All 42 chips- Alibaba T-Head Zhenwu 810E96 GB HBM2e · Deployed
- Alibaba T-Head Zhenwu M890144 GB HBM · Announced
- AWS Graviton5192 cores · TSMC 3 nm · Deployed
- Baidu Kunlunxin M100Announced
- Baidu Kunlunxin M300Announced
- Huawei Ascend 950DT144 GB HiZQ 2.0 (Huawei in-house HBM) · 1,000 FP8 TFLOPS · Sampling
- Huawei Ascend 950PR1,000 FP8 TFLOPS · Deployed
- Huawei Ascend 9602,000 FP8 TFLOPS · Announced
- Huawei Ascend 910C128 GB HBM · 752 BF16 TFLOPS · Deployed
- AWS Graviton496 cores · Deployed
- AWS Trainium296 GB HBM · 1,299 FP8 TFLOPS · Deployed
- Microsoft Cobalt 100128 cores · Deployed
- AWS Inferentia232 GB HBM · 190 BF16 TFLOPS · Deployed
- Huawei Ascend 910B64 GB HBM2e · 400 FP16 TFLOPS · Deployed
- AWS Trainium32 GB HBM · 190 BF16 TFLOPS · Deployed
- AWS Inferentia8 GB DRAM (not HBM) · 64 BF16 TFLOPS · Deployed
- Baidu Kunlunxin P80096 GB HBM · 345 FP16 TFLOPS · Deployed