GeekRadar / The comparison desk
COMPARE.
GPUNVIDIA GeForce RTX 4090 48 GB
Graphics processor
- Video memory
- 48 GB*
- Memory bus
- 384 bit*
- Rated memory bandwidth
- 1,010 GB/s*
No matched benchmark results are available for this entry yet.
Processing & platform
- Architecture
- Ada Lovelace*
- GPU cores
- 16,384*
- Graphics interface
- PCIe 4.0 x16*
- GPU L2 cache
- 72 MB*
- Texture mapping units
- 512*
- Streaming multiprocessors
- 128*
- Ray tracing cores
- 128*
- Card or module format
- Dual-slot*
- Declared GPU TDP
- 450 W*
- Suggested system PSU
- 850 W*
- External power connectors
- 1x 16-pin*
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenGL
- 4.6*
- OpenCL
- 3.0*
- Vulkan
- 1.4*
- CUDA compute capability
- 8.9*
Memory & storage
- Memory options
- 48*
- Video memory
- 48 GB*
- Video memory type
- GDDR6X*
- Memory bus
- 384 bit*
- Rated memory bandwidth
- 1,010 GB/s*
Power specifications
- Thermal design power
- 450 W*
System configuration
Detailed specifications
Specifications 1 · 25 fields
- cores
- 16,384*
- rt cores
- 128*
- sm count
- 128*
- base clock
- 2,235*
- boost clock
- 2,520*
- memory clock
- 1,313*
- ram
- 48*
- name
- NVIDIA GeForce RTX 4090 48 GB*
- ram type
- GDDR6X*
- bus width
- 384*
- bus interface
- PCIe 4.0 x16*
- ram bandwidth
- 1.01 TB/s*
- fp16 performance
- 82.58*
- fp32 performance
- 82.58*
- tdp
- 450* W
- suggested psu
- 850* W
- slot width
- Dual-slot*
- power connectors
- 1x 16-pin*
- api cuda
- 8.9*
- is retail board
- Yes*
- gpi value
- 35.58*
- vendor
- nvd*
- manufacturer
- NVIDIA*
- arch name
- Ada Lovelace*
- card release date
- 2022-09-20*
Specifications 2 · 27 fields
- CUDA compute capability
- 8.9*
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenCL
- 3.0*
- OpenGL
- 4.6*
- Vulkan
- 1.4*
- Architecture
- Ada Lovelace*
- Graphics interface
- PCIe 4.0 x16*
- Memory bus
- 384* bit
- Reported shader processors
- 16,384*
- Reported theoretical FP16 peak
- 82.58* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP32 peak
- 82.58* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Declared GPU L2 cache
- 72 MB*
- Reported display outputs
- HDMI, DisplayPort*
- External power connectors
- 1x 16-pin*
- Reported video memory
- 48* GB
- Rated memory bandwidth
- 1.01 TB/s*
- Video memory type
- GDDR6X*
- Ray tracing cores
- 128*
- Card or module format
- Dual-slot*
- Streaming multiprocessors
- 128*
- Suggested system PSU
- 850 W*
- 2:4 tensor sparsity
- Yes*
- Declared GPU TDP
- 450 W*
- Texture mapping units
- 512*
- GPU cores
- 16,384*
- Video memory
- 48* GB
- Video memory type
- GDDR6X*
0 selected Compare 0
* Provisional data