NVIDIA GeForce 820M
The NVIDIA GeForce 820M is a graphics card released on February 1, 2014, built on the Fermi architecture. It has 2 GB of DDR3 memory on a 64-bit bus, 16.0 GB/s of memory bandwidth and a 15 W board power rating. It scores 479 in the PassMark G3D benchmark. It supports DirectX 12, OpenGL 4.5 and CUDA compute capability 2.1.
Depth: 31 recorded fields, 1 feature, 4 PassMark workloads
Specification data last verified October 1, 2026 against PassMark Videocard Benchmark and Wikipedia GPU list tables (wikigrid-2026-09). Coverage: 8 of 10 tracked specifications recorded.
Performance
The NVIDIA GeForce 820M scores 479 in the PassMark G3D benchmark, higher than 35.6% of the 2,658 GPUs benchmarked (PassMark rank #1,914), measured across 2,777 submitted results. Its PassMark G2D score is 114.
PassMark workload tests
In the PassMark workload tests the NVIDIA GeForce 820M averages DirectX 9 10 fps, DirectX 10 2 fps, DirectX 11 5 fps and GPU Compute 479 ops/s, across 2,777 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.
As stated by PassMark
PassMark's own listing for the NVIDIA GeForce 820M states the PCIe 2.0 x16 interface, up to 2 GB of memory, a core clock of 954 MHz, DirectX 11 and OpenGL 4.5, first benchmarked on 2014-07-05. These are PassMark's figures, shown separately from the specification tables above.
Graphics processor
The NVIDIA GeForce 820M is based on the Fermi architecture and uses the GF117 graphics processor.
Memory
The NVIDIA GeForce 820M is equipped with 2 GB of DDR3 memory, uses a 64-bit memory bus and delivers 16.0 GB/s of memory bandwidth.
Board and power
The NVIDIA GeForce 820M has a board power rating of 15 W and it connects over PCIe 2.0 x16.
Market
The NVIDIA GeForce 820M was released on February 1, 2014.
Benchmarks
Graphics and compute APIs
The NVIDIA GeForce 820M supports DirectX 12, OpenGL 4.5 and CUDA compute capability 2.1.
Feex has no recorded Vulkan version for the NVIDIA GeForce 820M. Feex has no recorded OpenCL version for the NVIDIA GeForce 820M.
Features
The NVIDIA GeForce 820M 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 2.1Support 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 GeForce 820M supports Tensor cores and NVLink / SLI. That is silence, not a statement that they are unsupported.
The NVIDIA GeForce 820M supports CUDA (Compute capability 2.1) under Compute and AI.
Naming and aliases
The NVIDIA GeForce 820M is also known by other names: PassMark also lists it as NVIDIA GeForce 820M (Mobile).
Frequently asked questions
How much VRAM does the NVIDIA GeForce 820M have?
The NVIDIA GeForce 820M has 2 GB of DDR3 memory on a 64-bit bus. Its memory bandwidth is 16.0 GB/s.
How much power does the NVIDIA GeForce 820M use and what power supply does it need?
The NVIDIA GeForce 820M has a board power rating of 15 W.
How fast is the NVIDIA GeForce 820M?
The NVIDIA GeForce 820M scores 479 in the PassMark G3D benchmark, higher than 35.6% of the 2,658 GPUs benchmarked. Its PassMark rank is #1,914.
What is the CUDA compute capability of the NVIDIA GeForce 820M?
The NVIDIA GeForce 820M has CUDA compute capability 2.1.
What bus interface does the NVIDIA GeForce 820M use?
The NVIDIA GeForce 820M connects over PCIe 2.0 x16.
When was the NVIDIA GeForce 820M released?
The NVIDIA GeForce 820M was released on February 1, 2014.
Corrections to this record
After an audit, 1 empty field was filled from sources. Each change is listed with its old value, new value, rule and sources.
1 filled value
- Architecture: Fermi (was Not recorded). Rule: Architecture from chip codename. chip GF117 -> Fermi. Sources: Wikipedia: List of Nvidia graphics processing units (revision 1377107724).
The audit log is public: all changes for this GPU, the corrections overview and the method.