NVIDIA GRID K120Q
NVIDIA graphics card specifications and benchmark scores
At a Glance
NVIDIANVIDIA GRID K120Q Specifications
GRID K120Q GPU Core
Shader units and compute resources
The NVIDIA GRID K120Q GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.
GRID K120Q Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the GRID K120Q's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The GRID K120Q by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's GRID K120Q Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GRID K120Q's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.
GRID K120Q by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the GRID K120Q, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.
GRID K120Q Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA GRID K120Q against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.
Kepler Architecture & Process
Manufacturing and design details
The NVIDIA GRID K120Q is built on NVIDIA's Kepler architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the GRID K120Q will perform in GPU benchmarks compared to previous generations.
NVIDIA's GRID K120Q Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA GRID K120Q determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the GRID K120Q to maintain boost clocks without throttling.
GRID K120Q by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA GRID K120Q are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.
NVIDIA API Support
Graphics and compute APIs
API support determines which games and applications can fully utilize the NVIDIA GRID K120Q. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.
GRID K120Q Product Information
Release and pricing details
The NVIDIA GRID K120Q is manufactured by NVIDIA as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the GRID K120Q by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
GRID K120Q Benchmark Scores
No benchmark data available for this GPU.
About NVIDIA GRID K120Q
The NVIDIA GRID K120Q is an end-of-life GPU from the GRID (K1) generation, built around the GK107 chip on a 28 nm TSMC process. The die contains 1,270 million transistors on 118 mm², with a transistor density of 10.8M per mm². It is classified as an IGP, uses a PCIe 3.0 x16 bus interface, and provides no display outputs. The release date is 2014-07-01, and the launch MSRP is 125 USD. The product record stands out because it has no recorded benchmark runs, an average benchmark score of zero, and a 50th percentile ranking across all GPUs.
Benchmark Performance
The most important fact about the K120Q's performance records is that they are effectively empty. The benchmarks array contains no entries, the nearestRivals array contains no entries, and the average benchmark score is recorded as zero. That zero is not a measured performance result; it means no workloads have been submitted. The 50th percentile in percentileVsAllGpus should be read with the same caution. Without a score behind it, that percentile is a database placement rather than evidence of a verified mid-pack performance result.
What the record does provide is a complete set of fixed-function rates. The GPU contains 192 shading units, 16 TMUs, and 16 ROPs. FP32 throughput is 326.4 GFLOPS, texture rate is 13.60 GTexel/s, and pixel rate is 3.400 GPixel/s. No FP16 figure is present, so half-precision throughput is not characterized. The TMU and ROP counts are equal at 16, meaning texture and pixel work share balanced fixed-function resources. These are small figures on their own: 326.4 GFLOPS, 13.60 GTexel/s, and 3.400 GPixel/s set absolute limits on how much work the silicon can process per second.
Since the nearestRivals list is empty, there are no deltaPct values and no rival names to use in a percentage comparison. It is not possible to state that this card is a certain percentage faster or slower than any specific competitor. Any percentage claim would be unsupported by the FACT PACK. The data simply shows a GPU with constrained compute and fillrate, and the measured context that would normally accompany those specifications is absent.
Who Should Consider It
The K120Q is not a card for direct monitor use. Its displayOutputs field reads "No outputs", and its slotWidth is IGP, meaning it lacks a physical display path. The generation label GRID (K1) orients the product toward server-side graphics, where a host GPU renders frames for delivery to remote clients. That is the environment in which the card's design makes sense.
For virtual desktop deployments, the memory footprint is the central consideration. 512 MB of DDR3 means every active session must keep its framebuffer, textures, and render targets within that space. The 128-bit bus and 28.51 GB/s bandwidth then govern how quickly those resources can be accessed. The power envelope is modest at a 130 W TDP with a 300 W suggested PSU, but the memory and fillrate figures are far more restrictive for actual workloads.
There are no benchmark scores on which to base resolution and settings guidance. The relevant data points are 512 MB of VRAM, 28.51 GB/s of bandwidth, 3.400 GPixel/s pixel throughput, and 13.60 GTexel/s texture throughput. That combination points toward low-resolution remote desktops with conservative texture quality rather than high-resolution interactive sessions. Deployments targeting high pixel counts or detailed 3D content should treat the missing benchmark data as a signal that validation is required before relying on the card.
Ray Tracing and Feature Set
The GRID K120Q has no ray tracing cores and no tensor cores: both fields are null. The architecture is Kepler, with a release date of 2014-07-01, and the record contains no RT or tensor hardware. Features that depend on tensor cores or ray tracing acceleration are therefore not available on this GPU.
API support is broader than the hardware feature set. The GPU supports DirectX 12, with the feature level given as 11_0. It also supports OpenGL 4.6 and Vulkan 1.2.175. The DirectX 12 (11_0) designation means the GPU works with the DirectX 12 API but is capped at 11_0 feature-level capabilities. Vulkan 1.2.175 and OpenGL 4.6 are current cross-platform API targets for developers. No FP16 rate is listed, and without RT or tensor cores, the card has no hardware path for accelerated ray tracing or tensor-based workloads.
FAQ
Q: How much memory does the GRID K120Q have?
A: It has 512 MB of DDR3 memory on a 128-bit bus, with an 891 MHz memory clock, an effective data rate of 1782 Mbps, and 28.51 GB/s of bandwidth.
Q: Does the K120Q support hardware ray tracing?
A: No. The RT core field is null and the tensor core field is null. The GPU uses the Kepler architecture, and no ray tracing or tensor hardware is recorded.
Q: What display outputs does it provide?
A: The FACT PACK lists "No outputs". The slot width is IGP, so there are no direct display connectors.
Q: What APIs are supported?
A: DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175 are the supported APIs in the FACT PACK.
Q: What is the power requirement?
A: The TDP is 130 W and the suggested PSU is 300 W. No power connector details are listed.
Q: Are there benchmark scores for this card?
A: No. The benchmarks array is empty and the average benchmark score is zero, so no measured performance data exists in the record.
How It Compares
The nearestRivals array is empty, so no named competitors and no deltaPct percentages are available. This prevents any direct comparison with percentage precision. The only relative value is the 50th percentile in percentileVsAllGpus, but given the zero average benchmark score, that percentile is not supported by a measurement history. It should not be interpreted as a verified mid-pack performance result.
There are no rival paragraphs to write from this FACT PACK because no rival data is present. In the absence of a rival list, the internal specifications are the only basis for positioning: 192 shading units, 16 TMUs, 16 ROPs, 326.4 GFLOPS, 13.60 GTexel/s, 3.400 GPixel/s, 512 MB of VRAM, and 28.51 GB/s of bandwidth. These values describe a GPU with limited capacity across every measured axis. A precise competitive ranking would require nearestRivals data that the FACT PACK does not include.
Memory Subsystem
The memory subsystem is built around 512 MB of DDR3 on a 128-bit bus. The memory clock is 891 MHz, described as 1782 Mbps effective, and the resulting bandwidth is 28.51 GB/s. These are the only memory specifications present, and they are tightly interconnected: the bus width determines how much data can move per clock, the clock determines transfer rate, and the capacity limit determines how much data can remain resident.
For high resolutions, the implications are direct. 512 MB must contain color buffers, depth buffers, geometry data, and every texture that a scene touches. A large framebuffer with high color depth consumes a substantial portion of that space before textures are even loaded. The 128-bit bus and 28.51 GB/s bandwidth then set the speed at which those textures stream in. Alongside the 3.400 GPixel/s pixel rate, the memory system caps the card at workloads with modest resolution and restrained texture budgets. The data provides no evidence that this card can handle high-resolution rendering without major compromises.
Compare GRID K120Q with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs