AI chip · Google
Google TPU v5e
Cost-efficient TPU generation optimized for inference and smaller training runs; the mainstream Google Cloud TPU offering.
On the DEPLOY graph: 1 campus carry a cited inventory line for it.
Market position
Fifth-generation inference-optimised TPU. Cheaper per-chip than v5p, positioned against NVIDIA L4 for cost-sensitive inference on Google Cloud. Superseded by v6e for new deployments.
DEPLOY editorial. What the vendor PDF cannot tell you.
Physical-AI cross-link
Derived from claims already on record (vendor first-party TDP, throughput, price, and the reference-design cluster registry). The arithmetic is shown per row so it can be audited. No estimated inputs.
- Perf per watt
- 1.16 BF16 TFLOPS/W197 TFLOPS ÷ 170 W = 1.16
What fits in 16 GB
Weights-only footprint for public open-weight LLMs. Pure arithmetic: params × bytes/param. Excludes KV cache and activation memory; add ~10-30% headroom for real serving. A model that does not fit at FP16 may still fit at INT8 or INT4 with quality trade-offs. Not a benchmark.
| Model | Params | FP16 | INT8 | INT4 |
|---|---|---|---|---|
| Llama 3.1 8B dense | 8 B | 16 GB ✓ | 8 GB ✓ | 4 GB ✓ |
| Llama 3.1 70B dense | 70 B | 140 GB ✗ | 70 GB ✗ | 35 GB ✗ |
| Llama 3.1 405B dense | 405 B | 810 GB ✗ | 405 GB ✗ | 203 GB ✗ |
| Llama 3.3 70B dense | 70 B | 140 GB ✗ | 70 GB ✗ | 35 GB ✗ |
| DeepSeek V3 MoE (671B total, 37B active per token) | 671 B | 1342 GB ✗ | 671 GB ✗ | 336 GB ✗ |
| DeepSeek R1 MoE (671B total, 37B active per token) | 671 B | 1342 GB ✗ | 671 GB ✗ | 336 GB ✗ |
| Qwen 2.5 7B dense | 7 B | 14 GB ✓ | 7 GB ✓ | 4 GB ✓ |
| Qwen 2.5 72B dense | 72 B | 144 GB ✗ | 72 GB ✗ | 36 GB ✗ |
| Mixtral 8x7B MoE (46.7B total, 12.9B active per token) | 46.7 B | 93 GB ✗ | 47 GB ✗ | 23 GB ✗ |
| Mixtral 8x22B MoE (141B total, 39B active per token) | 141 B | 282 GB ✗ | 141 GB ✗ | 71 GB ✗ |
| Gemma 2 27B dense | 27 B | 54 GB ✗ | 27 GB ✗ | 14 GB ✓ |
| Command R+ dense | 104 B | 208 GB ✗ | 104 GB ✗ | 52 GB ✗ |
| Kimi K2 MoE (1T total, 32B active per token) | 1000 B | 2000 GB ✗ | 1000 GB ✗ | 500 GB ✗ |
Math: FP16 = params × 2 bytes; INT8 = params × 1 byte; INT4 = params × 0.5 bytes. MoE models sum every expert (full weights on disk), not the per-token active subset.
Common questions
Answer-first, sourced. Every claim below traces to a specific field on this page or a cited datasheet. FAQPage schema is emitted so LLM crawlers can lift these verbatim.
How much does Google TPU v5e cost?
Google TPU v5e launch pricing is not on record in the DEPLOY registry. Vendor list prices are typically published in the vendor's own briefing rather than the datasheet.
How much memory does Google TPU v5e have?
16 GB of HBM2 at 819 GB/s. Vendor datasheet, first-party.
How much power does one Google TPU v5e draw?
170 W TDP (thermal design power) per chip. System-level draw is higher: see the reference-design section for rack-level kW.
Which data centers have Google TPU v5e?
1 campus on the DEPLOY registry carry a cited inventory line for this chip. Full list below with per-campus quantity hints where published.
Which open-weight LLMs fit on one Google TPU v5e?
Of the 13 public open-weight LLMs DEPLOY tracks: 2 fit at FP16, 2 at INT8, 3 at INT4 (weights only, excludes KV cache). The full table is above with per-model math. Sparsity, offloading and multi-GPU serving change the picture; this row is single-chip weights-only.
Key facts
- Class
- Compute SoC (AI accelerator)
- Designer
- Safety-critical?
- No (data-center inference / training)
- Record as of
- 2026-08-25
- Latest cited claim
- 2024-01-01 (across 1 inventory + benchmark row)
Specifications (8 fields, click to expand)
Vendor datasheet figures (first-party). Dense throughput first; sparse (2:4) in parentheses where NVIDIA quotes it. The exhaustive spec sheet lives on the datasheet URL below the table: this row set covers what buyers actually compare on.
- TDP
- 170 W
- Memory
- 16 GB HBM2
- Memory bandwidth
- 819 GB/s
- BF16 (dense)
- 197 TFLOPS
- INT8 (dense)
- 393 TOPS
- Form factor
- OAM (v5e pod, up to 256 chips)
- Announced
- 2023-08-29
- Released
- 2023-11-01
Source: vendor datasheet
Generation
Compare with
Data centers stocking Google TPU v5e
Who has the most? →Every campus on the DEPLOY registry with a public claim of Google TPU v5e on site. Quantity hints are unstructured because underlying disclosures vary by order of magnitude.
- Google Dorchester & Berkeley County Data Center Campusesas of 2024-01-01under constructionreported
us-east4-adjacent TPU v5e capacity
Sources
- Cloud TPU v5eGoogle Cloud
Adoption rows appear as we verify chip-integration claims per model. Every row is a public claim the maker or a tier-1 source has stated; verification tier (verified / reported / inferred) is shown per row. See every chip on record for the full catalog or the Google record.