NVIDIA Jetson AGX Thor T5000 128GB vs NVIDIA GB200 Grace Blackwell Superchip 372GB

The GB200 delivers 19.3x the FP8 throughput of the Jetson AGX Thor (10,000 vs 517 TFLOPS dense). The GB200 also carries 244 GB more memory (372 GB vs 128 GB).

Jetson AGX Thor: Blackwell, 2025 GB200: Blackwell, 2024
FP8 dense lead
19.3x
GB200: 10,000 vs 517 TFLOPS
VRAM
128 vs 372 GB
244 GB more for the GB200
Bandwidth
273 GB/s vs 16.0 TB/s
GB200 moves data faster

Specifications

Jetson AGX Thor
GB200
Architecture
BlackwellBlackwell
Launch Year
20252024
Form Factor
ModuleSuperchip
VRAM
128 GB372 GB
Memory Bandwidth
273 GB/s16.0 TB/s
TDP
130 W
Process Node
4nm

Performance (TFLOPS)

Jetson AGX Thor
GB200
FP64
No verified data available80.0 TFlops
FP32
8.1 TFlops 160.0 TFlops
TF32
No verified data available2500.0 TFlops
5000.0 TFLOPS sparse
BF16
No verified data available5000.0 TFlops
10000.0 TFLOPS sparse
FP16
No verified data available5000.0 TFlops
10000.0 TFLOPS sparse
FP8
517.0 TFlops
1035.0 TFLOPS sparse
10000.0 TFlops
20000.0 TFLOPS sparse
FP6
No verified data available10000.0 TFlops
20000.0 TFLOPS sparse
FP4
1035.0 TFlops
2070.0 TFLOPS sparse
20000.0 TFlops
40000.0 TFLOPS sparse
INT8
517.0 TFlops
1035.0 TOPS sparse
10000.0 TFlops
20000.0 TOPS sparse

FLOPS by Precision

What actually differs

The Jetson AGX Thor is the newer part: Blackwell, launched in 2025, against the GB200's Blackwell from 2024. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the Jetson AGX Thor against the GB200: FP32 8.1 vs 160 TFLOPS, FP8 517 vs 10,000 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 128 GB against 372 GB, fed at 273 GB/s versus 16.0 TB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.

Frequently asked questions

Is the Jetson AGX Thor faster than the GB200?

At FP8 precision the GB200 reaches 10,000 TFLOPS dense against 517 TFLOPS for the Jetson AGX Thor. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the Jetson AGX Thor or the GB200?

The GB200 carries 372 GB of VRAM versus 128 GB for the Jetson AGX Thor. Memory bandwidth is 273 GB/s for the Jetson AGX Thor and 16.0 TB/s for the GB200.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.