Jetson AGX Thor T5000 for Edge AI — Specs, Sizing & Deployment Fit
Last updated: September 2026
NVIDIA’s generative-AI edge flagship: Blackwell-generation FP4 compute, 128 GB unified memory, and enough throughput for 70B-class on-device LLMs, VLA robotics models, and very high stream densities.
Planning Takeaway
NVIDIA’s generative-AI edge flagship: Blackwell-generation FP4 compute, 128 GB unified memory, and enough throughput for 70B-class on-device LLMs, VLA robotics models, and very high stream densities. Justify the ~$4,999 module (and 130 W envelope) with those workloads — for classical vision, AGX Orin remains the better spend.
Specifications
| Spec | Value |
|---|---|
| Compute | 2,070 TOPS-class FP4 (Blackwell GPU); NVFP4 + FP8 Transformer Engine |
| Memory | 128 GB unified, ~273 GB/s |
| Power envelope | 40–130 W |
| Video decode (datasheet, 120 W) | H.265 156× 1080p30 / 36× 4K30 · H.264 160× 1080p30 / 40× 4K30 (source) |
| Est. planning capacity | ~32 concurrent 1080p detection streams (planning cap) |
| Multi-instance GPU (MIG) | Tech preview on T5000 |
| Cooling | Active required |
| Form factor | Jetson AGX module (100×87 mm) |
| Software | JetPack 7.2 (Ubuntu 24.04, CUDA 13, June 2026) — current; JetPack 6.x (Ubuntu 22.04) — legacy track; production JetPack 7.1 shipped Jan 2026 with the TensorRT Edge-LLM SDK |
| Indicative price | ~$4,999 module / ~$5,499 dev kit (as of mid-2026) |
Sizing Fit
Built for on-device generative AI: 30B–70B LLMs, vision-language-action robotics, multi-model concurrency with hard isolation, and stream densities beyond AGX Orin.
Decision Framework
Choose the Thor T5000 if:
- You run 30B+ parameter LLMs or VLA models on-device — NVFP4 and 128 GB are the enablers.
- You need multiple concurrent models with real-time isolation (MIG is a tech preview on T5000).
- Stream density beyond ~20 concurrent cameras on a single node matters more than power draw.
Choose a sibling instead if:
- Jetson T4000 — you want the Thor generation at ~$2,999 with a lower power and thermal envelope.
- Jetson AGX Orin 64GB — classical vision and ≤13B LLMs — it remains the production workhorse at ~$2,999.
Video decode & encode (datasheet)
Hardware codec limits for the Jetson Thor T5000 as NVIDIA publishes them at 120 W. Streams per module at 1080p30 and 4K30, rated decoder throughput, and NVENC streams at 1080p30. Full profile tables, sources and class-D interpolation: decode capacity for the Jetson Thor T5000.
| Codec | Decode 1080p30 | Decode 4K30 | Decode MP/s | Encode 1080p30 |
|---|---|---|---|---|
| H.265 | 156 | 36 | 4920 | 100 |
| H.264 | 160 | 40 | 5040 | 88 |
| AV1 | 96 | 24 | 3120 | — |
| VP9 | 116 | 28 | 3780 | — |
NVIDIA · DS-11945-001 v1.5 §2.2 Multi-Standard Video Decoder, Table 2-2 (T5000), 120W Mode · verified 2026-09-07 · Jetson Thor Series Modules Data Sheet · class A
Production carriers
1 carrier board, system and developer kit in the registry list the Jetson Thor T5000, each with power, camera, Ethernet/PoE, expansion and price cited to the vendor or a reseller. Full ranked table and common-needs shortlist: production carriers for the Jetson Thor T5000.
- NVIDIA Jetson AGX Thor Developer Kit (reference carrier) (developer kit, $5,499)
Frequently Asked Questions
How much does Jetson Thor cost?
As of the July 2026 NVIDIA repricing, the Thor T5000 module lists at ~$4,999 (up from $2,999) and the AGX Thor Developer Kit at ~$5,499 (launched August 2025 at $3,499). The T4000 module lists at ~$2,999.
Is Thor worth it over the AGX Orin 64GB?
Only if you are running 30B+ parameter LLMs, Vision-Language-Action models, or many concurrent models on one device. For multi-stream vision and LLMs up to ~13B parameters, the AGX Orin 64GB at ~$3,499 (dev kit) remains the better choice — Thor’s price, 130 W draw, and cooling needs rule it out for constrained deployments.
What is special about Thor’s FP4 support?
NVFP4 is NVIDIA’s block-scaled 4-bit floating-point format: FP4 weights with FP8 activations, switched at runtime by the Transformer Engine. It is what lets a 70B-parameter model fit in 128 GB of unified memory with room for KV cache — AGX Orin (Ampere) has no FP4 hardware.
What JetPack does Thor run?
JetPack 7.2 (June 2026) is current — Ubuntu 24.04, CUDA 13 — across Thor and the Orin family. Thor’s production software line began with JetPack 7.1 (January 2026), which introduced the TensorRT Edge-LLM SDK. MIG on the T5000 is a tech preview.