NVIDIA Jetson Thor
2,560
CUDA Cores
128GB
VRAM
273
GB/s
Technical Specifications
2,560
CUDA Cores
1570
Base MHz
1570
Boost MHz
128GB LPDDR5X
256-bit bus
Performance
15
FP32 TFLOPS
80
FP16 TFLOPS
130W
TDP
Cloud Availability
0
Available Instances
$0.00/hr
Starting Price
Detailed Specifications
| Architecture | Blackwell (Unknown) |
| Release Date | 2024-01-15 |
| Launch Price | $3,499.00 |
| Process | 4nm |
| Transistors | 100B |
AI Features
Gen 5
Tensor Cores
Enabled
Transformer Engine
Supported
Flash Attention
Physical Specifications
Dimensions
9.57in
Length
4.42in
Width
2.24in
Height
About Jetson Thor GPU
The NVIDIA Jetson Thor was introduced in 2024 on the Blackwell architecture. Its specification combines 2,560 CUDA cores with 128GB of LPDDR5X, which defines both the workloads it can run and the batch sizes it can hold.
Based on its 128GB memory capacity, the Jetson Thor is best evaluated for large-model training, high-batch inference, and memory-intensive scientific computing. Always size the model, optimizer state, KV cache, and framework overhead together rather than choosing a GPU from core count alone.
GPUvec does not currently have an active hourly cloud listing for the Jetson Thor. This is not a zero-dollar offer: it means no comparable provider price is available in the present dataset. Check the provider directory for availability or compare a related GPU with an active listing.
For software planning, the Jetson Thor combines 273 GB/s of memory bandwidth, CUDA compute capability the latest, and a 4nm manufacturing process. Confirm the minimum CUDA, PyTorch, TensorFlow, or driver version required by your application before renting or purchasing hardware.
External Resources
Learn more about GPUs from these authoritative sources:
Official CUDA programming guide
NVIDIA GPU Specifications →Official NVIDIA GPU specs
TechPowerUp GPU Database →Comprehensive GPU specifications
CUDA Compute Capability Guide →GPU compute capability reference
What You Need to Know About the Jetson Thor
Complete Specifications for the NVIDIA Jetson Thor
The NVIDIA Jetson Thor uses the Blackwell architecture and combines 2,560 CUDA cores with 128GB of LPDDR5X. GPUvec records 273 GB/s memory bandwidth alongside architecture, release date, process node, accelerator features, and physical specifications so the page can be evaluated from source data instead of model-name assumptions.
Compare NVIDIA Jetson Thor Cloud Rental Prices per Hour
GPUvec currently has no comparable active hourly listing for this model; this means pricing is unavailable, not free. Provider rates can vary by region, host configuration, billing model, and availability. Use the provider directory and related-GPU links to compare an available alternative when this exact accelerator is not listed.
Is the NVIDIA Jetson Thor the Right GPU for Your AI Workload?
Start with the 128GB memory limit, then evaluate 273 GB/s memory bandwidth, compute features, and software compatibility for your workload. Model weights, KV cache, activations, optimizer state, and framework overhead all consume memory. Compare this page with related accelerators rather than assuming that a higher core count alone guarantees a better training or inference result.
Top GPUs for Training and Inference
| Category | Rank 1 | Rank 2 | Rank 3 |
|---|---|---|---|
| Best for Training | NVIDIA H200 | NVIDIA H100 | NVIDIA B200 |
| Best for Inference | NVIDIA A40 | NVIDIA A100 | NVIDIA A10 |
Compare GPU specifications and cloud instances to find the best GPU for your workload.