Jetson Orin Nano (8GB / 4GB) AV1 decode capacity
Dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026
NVIDIA rates the Jetson Orin Nano (8GB / 4GB) NVDEC at 1 × 4K60 · 2 × 4K30 · 5 × 1080p60 · 10 × 1080p30 AV1 (625 MP/s), in every power mode.
Verbatim datasheet figures with their source. Anything not in the table below is an EdgeAIStack estimate and is labelled as such. Jetson Orin Nano platform page · Jetson Orin Nano Super platform page.
Published decode points (class A)
Jetson Orin Nano (8GB / 4GB): 1 NVDEC instance, AV1 profile Main, 8-bit 4:2:0 unless the datasheet says otherwise. Stream counts are per module.
| Profile | Pixels @ fps | Streams (module) | MP/s per stream | Streams × MP/s | Evidence |
|---|---|---|---|---|---|
| 4K60 | 3840×2160 @ 60 | 1 | 497.7 | 498 | A datasheet |
| 4K30 | 3840×2160 @ 30 | 2 | 248.8 | 498 | A datasheet |
| 1080p60 | 1920×1080 @ 60 | 5 | 124.4 | 622 | A datasheet |
| 1080p30 | 1920×1080 @ 30 | 10 | 62.2 | 622 | A datasheet |
| Rated throughput (up to) | 625 MP/s | A datasheet | |||
Source
- NVIDIA · DS-11105-001 v1.1 §1.9.1 Multi-Standard Video Decoder, Table 5 · verified 2026-09-07 · Jetson Orin Nano Series Modules Data Sheet · class A
“AV1 Main Profile 4K60 (1) | 4K30 (2) | 1080p60 (5) | 1080p30 (10) 625 75”
v1.1 dated April 26 2023. One table covers the 8GB and 4GB modules.
Between the published points (class D)
Camera profiles NVIDIA does not print are estimated by comparing the pixel rate against the rated 625 MP/s: max streams = ⌊625 ÷ (width × height × fps ÷ 10⁶)⌋. These are EdgeAIStack numbers, not NVIDIA's; they assume roughly linear NVDEC throughput inside the published range and are not asserted outside it. Rows that coincide with a published point show the datasheet count instead.
| Profile | Pixels @ fps | MP/s per stream | Max streams (est.) | Evidence | Full pipeline |
|---|---|---|---|---|---|
| 720p30 | 1280×720 @ 30 | 27.6 | 22 | D pixel-rate | check the full pipeline |
| 1080p15 | 1920×1080 @ 15 | 31.1 | 20 | D pixel-rate | check the full pipeline |
| 1080p20 | 1920×1080 @ 20 | 41.5 | 15 | D pixel-rate | check the full pipeline |
| 1080p25 | 1920×1080 @ 25 | 51.8 | 12 | D pixel-rate | check the full pipeline |
| 1440p15 | 2560×1440 @ 15 | 55.3 | 11 | D pixel-rate | check the full pipeline |
| 1440p20 | 2560×1440 @ 20 | 73.7 | 8 | D pixel-rate | check the full pipeline |
| 1440p30 | 2560×1440 @ 30 | 110.6 | 5 | D pixel-rate | check the full pipeline |
| 4K15 | 3840×2160 @ 15 | 124.4 | 5 | D pixel-rate | check the full pipeline |
| 4K20 | 3840×2160 @ 20 | 165.9 | 3 | D pixel-rate | check the full pipeline |
| 4K25 | 3840×2160 @ 25 | 207.4 | 3 | D pixel-rate | check the full pipeline |
Power mode
NVDEC/NVENC maximum clock is the same in every nvpmodel power preset on Orin, so decode capacity does not change with the power mode.
Source
- NVIDIA · forums.developer.nvidia.com/t/380328 2026-08-17 · reply by NVIDIA staff (DaneLLL) · verified 2026-09-07 · NVIDIA Developer Forums — "Orin NX 16GB — NVDEC capacity for 4× 2560×1440 H.265 streams, and Super mode impact" · class A
“Maximum frequency of NVDEC is same in different power modes.”
Encode
Jetson Orin Nano (8GB / 4GB) has no hardware encoder (NVENC). The datasheet states: “1080p30 Supported via CPU Cores with Software”. Re-encoding or restreaming competes with inference for CPU cores; record camera streams as-is (passthrough) wherever possible.
Encode source
- NVIDIA · DS-11105-001 v1.1 · Functional Overview, Video Encode · verified 2026-09-07 · Jetson Orin Nano Series Modules Data Sheet · class A
“1080p30 Supported via CPU Cores with Software”
What these numbers do and do not cover
- Hardware limit, not software. JetPack, DeepStream, GStreamer or Frigate may cap concurrent decoder sessions below the datasheet count.
- Decode in isolation. Simultaneous NVENC use shares memory bandwidth; expect real decode + encode totals below the sum of the two tables.
- Profile and chroma. Counts are for Main at 8-bit 4:2:0; 4:4:4 halves throughput (datasheet note); Main10 shares the row.
- Decode is rarely the bottleneck. Inference, memory and preprocessing usually fail first on a detection pipeline; run the full pipeline check for your workload.
- Method. Formulas, evidence classes and the confidence rule are on the methodology page.
Other codecs on this module
AV1 on other modules
Is decode really the limit?
Run Jetson Orin Nano (8GB / 4GB) with your camera count, model and frame rate: every stage as a constraint, every number with its source, a permanent link.