AI chip · NVIDIA
NVIDIA DRIVE Thor
Automotive-safety-certified Blackwell-based SoC for L4 AV compute; adopted by Volvo, Polestar, XPENG, and others.
On the DEPLOY graph: 11 robots on record adopt this chip.
Market position
DRIVE Thor is Thor's automotive-safety-certified sibling: same silicon, ASIL-D chain-of-custody, packaged for ISO 26262 vehicle programs. Waymo Gen 6, Zoox, Pony.ai Gen 7, XPeng Robotaxi, WeRide and Momenta are the announced production programs.
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
- 15.38 FP8 TFLOPS/W2,000 TFLOPS ÷ 130 W = 15.38
What fits in 128 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 NVIDIA DRIVE Thor cost?
NVIDIA DRIVE Thor 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 NVIDIA DRIVE Thor have?
128 GB of LPDDR5X. Vendor datasheet, first-party.
How much power does one NVIDIA DRIVE Thor draw?
130 W TDP (thermal design power) per chip. System-level draw is higher: see the reference-design section for rack-level kW.
What runs on NVIDIA DRIVE Thor?
11 robot models on the DEPLOY registry adopt this chip, including Waymo Driver (6th gen), Zoox Robotaxi, Kodiak Driver, and 8 more. Full list below.
Which open-weight LLMs fit on one NVIDIA DRIVE Thor?
Of the 13 public open-weight LLMs DEPLOY tracks: 4 fit at FP16, 8 at INT8, 9 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
- NVIDIA
- Safety-critical?
- Yes (embedded / automotive)
- Record as of
- 2026-08-25
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.
- Process node
- TSMC 4NP
- TDP
- 130 W
- Memory
- 128 GB LPDDR5X
- FP8 (dense)
- 2,000 TFLOPS
- INT8 (dense)
- 2,000 TOPS
- Form factor
- Auto-board
- Announced
- 2022-09-20
- Released
- 2025-06-01
Source: vendor datasheet
Generation
Compare with
Robot models running NVIDIA DRIVE Thor
Every model on the DEPLOY registry with a public chip-integration claim for NVIDIA DRIVE Thor. Ranked by verified deployment count.
| Model | Maker | Form factor | Role | Source | Deployments |
|---|---|---|---|---|---|
| Waymo Driver (6th gen) | Waymo | av | onboard AV compute (Gen 6) | reported | 29 |
| Zoox Robotaxi | Zoox | av | onboard AV compute | reported | 19 |
| Kodiak Driver | Kodiak AI | truck | centralized AV compute | reported | 7 |
| Pony Gen-7 Robotaxi | Pony AI | av | Gen 7 domain controller | reported | 7 |
| Aurora Driver | Aurora Innovation | av | centralized AV compute | reported | 6 |
| Robotaxi GXR | WeRide | av | onboard AV compute | reported | 5 |
| Volvo EX90 | Volvo Cars | av | centralized AV compute | reported | 2 |
| Heron / DriveHeron | Turing | av | onboard AV compute | inferred | 1 |
| Momenta Robotaxi | Momenta Global | av | onboard AV compute | reported | 1 |
| Motional IONIQ 5 Robotaxi | Motional | av | centralized AV compute | reported | 1 |
| XPENG Robotaxi | XPeng Robotics | av | onboard AV compute | reported | 0 |
Sources
- NVIDIA DRIVE ThorNvidia
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 NVIDIA record.