NVIDIA A16
The NVIDIA A16 is a graphics card released on April 12, 2021, built on the Ampere architecture. It scores 5,281 in the PassMark G3D benchmark. It supports CUDA compute capability 8.6.
Depth: 16 recorded fields, 10 features, 5 PassMark workloads
Specification data last verified October 1, 2026 against PassMark Videocard Benchmark, NVIDIA Developer: CUDA GPUs, NVIDIA Developer: Video Encode and Decode GPU Support Matrix and Wikipedia GPU list tables (wikigrid-2026-09). Coverage: 4 of 10 tracked specifications recorded.
Performance
The NVIDIA A16 scores 5,281 in the PassMark G3D benchmark, higher than 81.2% of the 2,658 GPUs benchmarked (PassMark rank #521), measured across 5 submitted results. Its PassMark G2D score is 437.
PassMark workload tests
In the PassMark workload tests the NVIDIA A16 averages DirectX 9 43 fps, DirectX 10 25 fps, DirectX 11 17 fps, DirectX 12 16 fps and GPU Compute 2,208 ops/s, across 5 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.
As stated by PassMark
Not to be confused with
This page covers the NVIDIA A16 specifically. It is a different product from NVIDIA A16-16A, NVIDIA A16-16Q, NVIDIA A16-1B, NVIDIA A16-1Q, NVIDIA A16-2B, NVIDIA A16-2Q, which have their own specifications. Check the exact model name before comparing figures.
Graphics processor
The NVIDIA A16 is based on the Ampere architecture.
Memory
Market
The NVIDIA A16 was released on April 12, 2021.
Benchmarks
Graphics and compute APIs
The NVIDIA A16 supports CUDA compute capability 8.6.
Feex has no recorded Vulkan version for the NVIDIA A16. Feex has no recorded OpenCL version for the NVIDIA A16.
Features
The NVIDIA A16 has 1 supported feature recorded outside the media engine. A feature that no source mentions is shown as not listed, never as unsupported.
Compute and AI
-
Supported: CUDA Compute capability 8.6Support for NVIDIA's CUDA computing platform, used by many creative, scientific and AI applications.
Not listed (2)
No source Feex holds states whether the NVIDIA A16 supports Tensor cores and NVLink / SLI. That is silence, not a statement that they are unsupported.
The NVIDIA A16 supports CUDA (Compute capability 8.6) under Compute and AI.
Media engine
The NVIDIA A16 provides hardware encode for H.264 (AVC) and HEVC (H.265) and hardware decode for H.264 (AVC), HEVC (H.265), AV1 and VP9. It does not support hardware encode for AV1.
| Codec | Encode | Decode |
|---|---|---|
| H.264 (AVC) | Supported4:4:4: Yes | Supported |
| HEVC (H.265) | Supported4:2:2: No; 4:4:4: Yes; 10-bit: Yes; B-frames: Yes; 8K: Yes | Supported4:4:4: Yes |
| AV1 | Not supported | Supported |
| VP9 | Not stated by the vendor | Supported |
supported explicitly not supported not stated by the vendor
Media engines recorded for the NVIDIA A16: NVIDIA NVENC encoder (7th Generation, encoder engines: 4) and NVIDIA NVDEC decoder (5th Generation, decoder engines: 8).
Frequently asked questions
How fast is the NVIDIA A16?
The NVIDIA A16 scores 5,281 in the PassMark G3D benchmark, higher than 81.2% of the 2,658 GPUs benchmarked. Its PassMark rank is #521. In the PassMark DirectX 12 test it averages 16 fps.
Does the NVIDIA A16 support AV1 encoding?
No. Feex records AV1 hardware encoding as explicitly not supported on the NVIDIA A16, although it can decode AV1 in hardware.
What is the CUDA compute capability of the NVIDIA A16?
The NVIDIA A16 has CUDA compute capability 8.6.
When was the NVIDIA A16 released?
The NVIDIA A16 was released on April 12, 2021.