AI chip · NVIDIA
NVIDIA DRIVE Thor
Automotive-safety-certified Blackwell-based SoC for L4 AV compute; adopted by Volvo, Polestar, XPENG, and others.
Powers 11 tracked robots.
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.
Efficiency and power
How much work you get per watt and per dollar, and how much power a full rack draws.
- Perf per watt
- 15.38 FP8 TFLOPS/W2,000 TFLOPS ÷ 130 W = 15.38
What fits in 128 GB
Which open-source LLMs run on one NVIDIA DRIVE Thor, by precision. Weights only: add roughly 15% headroom for real serving. If a model does not fit at FP16, try INT8 or INT4 (smaller quality trade-off than most people expect).
| 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
How much does NVIDIA DRIVE Thor cost?
NVIDIA DRIVE Thor doesn't have a public launch list price. Vendors like this one usually price through direct sales rather than a public sheet. See list price per TFLOP for chips that do publish.
How much memory does NVIDIA DRIVE Thor have?
128 GB of LPDDR5X. Straight from the vendor datasheet. See chips with the most memory for context.
How much power does one NVIDIA DRIVE Thor draw?
130 W at the chip. A full server draws more once you add CPU, memory, networking and cooling: see the rack power number above. Compare to other chips on perf-per-watt.
What runs on NVIDIA DRIVE Thor?
11 robot models we track use this chip, including Waymo Driver (6th gen), Zoox Robotaxi and Aurora Driver, plus 8 more. Full list below.
Which open-source LLMs fit on one NVIDIA DRIVE Thor?
Of 13 open-source LLMs we track, 4 fit at FP16, 8 at INT8, and 9 at INT4 (for example Llama 3.1 8B, Llama 3.1 70B and Llama 3.3 70B). Full table above with each model's memory need.
Key facts
- Class
- Compute SoC (AI accelerator)
- Designer
- NVIDIA
- Safety-critical?
- Yes (embedded / automotive)
- Record as of
- 2026-09-27
Specifications (8 fields, click to expand)
Straight from the vendor datasheet. Dense throughput shown first; sparse (2:4) numbers in parentheses where the vendor publishes them. Full datasheet linked below.
- 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
Foundry & process
- Fabbed at
- TSMC (all chips TSMC makes →)
- Process node
- TSMC 4NP
Compare with
Robots running NVIDIA DRIVE Thor
Every robot model publicly known to ship NVIDIA DRIVE Thor inside it. Ranked by how widely each has been deployed.
| 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 |
| Aurora Driver | Aurora Innovation | av | centralized AV compute | reported | 7 |
| Kodiak Driver | Kodiak AI | truck | centralized AV compute | reported | 7 |
| Pony Gen-7 Robotaxi | Pony AI | av | Gen 7 domain controller | reported | 7 |
| 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 confirm each chip-in-robot pairing from a public source. See every chip we track for the full catalog or the NVIDIA page.