GPU Wiki
Compare GPUs
Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.
Popular comparisons
| Spec | P104-100 |
|---|---|
| Overview | |
| Product name | NVIDIA P104-100 |
| Architecture | Pascal |
| Generation / family | Mining GPUs |
| GPU codename | GP104 |
| Launch date | 2017-12-12 |
| Market segment | Desktop in Mining GPUs |
| Board type / entry type | Reference GPU |
| GPU | |
| Process node | TSMC 16 nm |
| Die size | 314 mm² |
| Transistor count | 7.2 billion |
| GPU chip | GP104 |
| SM / multiprocessor count | 15 |
| CUDA Cores | 1920 |
| ROPs | 64 |
| TMUs | 120 |
| Clocks | |
| Base / Core clock | 1,607 MHz |
| Boost clock | 1,733 MHz |
| Memory clock | 1,251 MHz |
| Memory | |
| Memory size | 4 GB |
| Memory type | GDDR5X |
| Memory bus width | 256-bit |
| Memory bandwidth | 320.3 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 1.0 x4 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 150 W |
| Recommended PSU | 200 W |
| Power connectors | 1x 8-pin |
| Slot width | Dual-slot, 267 mm length |
| Features | |
| DirectX support | DirectX 12.1 |
| OpenGL support | OpenGL 4.6 |
| Vulkan support | Vulkan 1.4 |
| CUDA support | 6.1 |
| Shader Model | 6.8 |
| Performance / Benchmarks | |
| FP32 throughput | 6.66 TFLOPS |
| FP16 throughput | 0.1 TFLOPS |
Overview
Product name
P104-100
NVIDIA P104-100
Architecture
P104-100
Pascal
Generation / family
P104-100
Mining GPUs
GPU codename
P104-100
GP104
Launch date
P104-100
2017-12-12
Market segment
P104-100
Desktop in Mining GPUs
Board type / entry type
P104-100
Reference GPU
GPU
Process node
P104-100
TSMC 16 nm
Die size
P104-100
314 mm²
Transistor count
P104-100
7.2 billion
GPU chip
P104-100
GP104
SM / multiprocessor count
P104-100
15
CUDA Cores
P104-100
1920
ROPs
P104-100
64
TMUs
P104-100
120
Clocks
Base / Core clock
P104-100
1,607 MHz
Boost clock
P104-100
1,733 MHz
Memory clock
P104-100
1,251 MHz
Memory
Memory size
P104-100
4 GB
Memory type
P104-100
GDDR5X
Memory bus width
P104-100
256-bit
Memory bandwidth
P104-100
320.3 GB/s
Bus / Interface
Bus interface
P104-100
PCIe 1.0 x4
AGP / PCI / PCIe distinction
P104-100
PCIe
Power
TDP / TBP / board power
P104-100
150 W
Recommended PSU
P104-100
200 W
Power connectors
P104-100
1x 8-pin
Slot width
P104-100
Dual-slot, 267 mm length
Features
DirectX support
P104-100
DirectX 12.1
OpenGL support
P104-100
OpenGL 4.6
Vulkan support
P104-100
Vulkan 1.4
CUDA support
P104-100
6.1
Shader Model
P104-100
6.8
Performance / Benchmarks
FP32 throughput
P104-100
6.66 TFLOPS
FP16 throughput
P104-100
0.1 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.