NVIDIA P104-100
Graphics processor
- Video memory
- 4 GB*
- Memory bus
- 256 bit*
- Rated memory bandwidth
- 320.30 GB/s*
Rendering performance
Three-scene Blender rendering throughput. Versions, operating systems and rendering backends remain separate. This is not a gaming score.
Community submissions; cooling, power limits and system configuration can affect results.
Graphics & compute benchmarks
GFXBench, GLBenchmark and CompuBench results retain the tested system, API, operating system and resolution. Offscreen tests fix the render resolution; onscreen results also reflect the display workload. These historical submissions do not establish performance in current games.
1080p ALU 2 OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA P104-100
1,430.38* fps
NVIDIA P104-100
Host configuration not reported.
1080p Driver Overhead 2 OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA P104-100
114.14* fps
NVIDIA P104-100
Host configuration not reported.
1080p Manhattan 3.1 OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA P104-100
318.84* fps
NVIDIA P104-100
Host configuration not reported.
1080p Manhattan OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA P104-100
387.39* fps
NVIDIA P104-100
Host configuration not reported.
1080p T-Rex OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA P104-100
1,419.34* fps
NVIDIA P104-100
Host configuration not reported.
1080p Texturing OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · MTexels/s
Higher is better.
NVIDIA P104-100
165,391* MTexels/s
NVIDIA P104-100
Host configuration not reported.
1440p Manhattan 3.1.1 OffscreenWindows / OpenGL / 2560 x 1440 / offscreen · fps
Higher is better.
NVIDIA P104-100
237.71* fps
NVIDIA P104-100
Host configuration not reported.
4K Aztec Ruins High Tier OffscreenWindows / OpenGL / 3840 x 2160 / offscreen · fps
Higher is better.
NVIDIA P104-100
67.02* fps
NVIDIA P104-100
Host configuration not reported.
Aztec Ruins High Tier OffscreenWindows / OpenGL / 2560 x 1440 / offscreen · fps
Higher is better.
NVIDIA P104-100
136.62* fps
NVIDIA P104-100
Host configuration not reported.
Aztec Ruins Normal Tier OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA P104-100
292.21* fps
NVIDIA P104-100
Host configuration not reported.
Car Chase OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA P104-100
243.75* fps
NVIDIA P104-100
Host configuration not reported.
Tessellation OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA P104-100
1,474.56* fps
NVIDIA P104-100
Host configuration not reported.
ALU 2Windows / OpenGL / 2560 x 1440 / onscreen · fps
Higher is better.
NVIDIA P104-100
48.01* fps
NVIDIA P104-100
Host configuration not reported.
Aztec Ruins High TierWindows / OpenGL / 2560 x 1440 / onscreen · fps
Higher is better.
NVIDIA P104-100
46.55* fps
NVIDIA P104-100
Host configuration not reported.
Aztec Ruins Normal TierWindows / OpenGL / 2560 x 1440 / onscreen · fps
Higher is better.
NVIDIA P104-100
47.42* fps
NVIDIA P104-100
Host configuration not reported.
Car ChaseWindows / OpenGL / 2560 x 1440 / onscreen · fps
Higher is better.
NVIDIA P104-100
43.45* fps
NVIDIA P104-100
Host configuration not reported.
Median results, not the best run. Sample counts and individual test dates are unreported. Different systems using the same GPU remain separate configurations.
Benchmark results
- Geekbench GPU (reported compilation) · version unreported · OpenCL52,593*Platform unreported Compare results
- Geekbench GPU (reported compilation) · version unreported · Vulkan48,169*Platform unreported Compare results
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Blender Cycles / classroomOPTIX / Linux · 4.4.0 · samples/min
NVIDIA P104-100
145.18 samples/min
7 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / Complete suiteOPTIX / Linux · 4.4.0 · samples/min
NVIDIA P104-100
593.59 samples/min
7 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
- 25th percentile
- 585.92135958974
- 75th percentile
- 596.32099686079
Blender Cycles / junkshopOPTIX / Linux · 4.4.0 · samples/min
NVIDIA P104-100
185.57 samples/min
7 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / monsterOPTIX / Linux · 4.4.0 · samples/min
NVIDIA P104-100
262.84 samples/min
7 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / classroomOPTIX / Windows · 4.0.0 · samples/min
NVIDIA P104-100
146.36 samples/min
5 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Windows
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / classroomOPTIX / Linux · 4.0.0 · samples/min
NVIDIA P104-100
145.94 samples/min
4 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / Complete suiteOPTIX / Windows · 4.0.0 · samples/min
NVIDIA P104-100
587.74 samples/min
5 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Windows
- Statistic
- Median
- Evaluation type
- community rendering submissions
- 25th percentile
- 577.83288124278
- 75th percentile
- 590.40513127291
Blender Cycles / Complete suiteOPTIX / Linux · 4.0.0 · samples/min
NVIDIA P104-100
593.04 samples/min
4 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
- 25th percentile
- 574.16105595904
- 75th percentile
- 594.85539267009
Blender Cycles / junkshopOPTIX / Windows · 4.0.0 · samples/min
NVIDIA P104-100
178.25 samples/min
5 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Windows
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / junkshopOPTIX / Linux · 4.0.0 · samples/min
NVIDIA P104-100
180.59 samples/min
4 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / monsterOPTIX / Windows · 4.0.0 · samples/min
NVIDIA P104-100
261.11 samples/min
5 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Windows
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / monsterOPTIX / Linux · 4.0.0 · samples/min
NVIDIA P104-100
266.46 samples/min
4 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / classroomOPTIX / Linux · 3.6.0 · samples/min
NVIDIA P104-100
147.79 samples/min
6 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / Complete suiteOPTIX / Linux · 3.6.0 · samples/min
NVIDIA P104-100
626.58 samples/min
6 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
- 25th percentile
- 624.36613931796
- 75th percentile
- 631.89065276121
Blender Cycles / junkshopOPTIX / Linux · 3.6.0 · samples/min
NVIDIA P104-100
191.92 samples/min
6 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / monsterOPTIX / Linux · 3.6.0 · samples/min
NVIDIA P104-100
287.23 samples/min
6 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / classroomOPTIX / Windows · 3.3.0 · samples/min
NVIDIA P104-100
146.96 samples/min
3 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Windows
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / Complete suiteOPTIX / Windows · 3.3.0 · samples/min
NVIDIA P104-100
625.83 samples/min
3 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Windows
- Statistic
- Median
- Evaluation type
- community rendering submissions
- 25th percentile
- 625.04487982087
- 75th percentile
- 626.32724196908
Blender Cycles / junkshopOPTIX / Windows · 3.3.0 · samples/min
NVIDIA P104-100
189.56 samples/min
3 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Windows
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / monsterOPTIX / Windows · 3.3.0 · samples/min
NVIDIA P104-100
289.29 samples/min
3 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Windows
- Statistic
- Median
- Evaluation type
- community rendering submissions
Processing & platform
- Architecture
- Pascal
- Manufacturing process
- 16 nm
- Process node
- 16 nm
- GPU cores
- 1,920*
- Reported GPU frequency
- 1,607 MHz*
- Graphics interface
- PCIe 1.0 x4*
- Reported chip die area
- 314 mm²*
- Transistors
- 7,200 million*
- GPU L2 cache
- 2 MB*
- Graphics processor
- GP104*
- Texture mapping units
- 120*
- Raster output units
- 64*
- Streaming multiprocessors
- 15*
- Chip foundry
- TSMC*
- Card or module format
- Dual-slot*
- Suggested system PSU
- 200 W*
- External power connectors
- 1x 8-pin*
- DirectX / feature level
- 12 (12_1)*
- OpenGL
- 4.6*
- OpenCL
- 3.0*
- Vulkan
- 1.4*
- CUDA compute capability
- 6.1*
- Shader model
- 6.8*
Memory & storage
- Memory options
- 4*
- Video memory
- 4 GB*
- Video memory type
- GDDR5X*
- Memory bus
- 256 bit*
- Rated memory bandwidth
- 320.30 GB/s*
System configuration
Detailed specifications
Specifications 1 · 12 fields
- Foundry
- TSMC*
- Vendor
- NVIDIA*
- FP16 GFLOPS
- 104* GFLOPS
- FP32 GFLOPS
- 6,655* GFLOPS
- FP64 GFLOPS
- 208* GFLOPS
- Product
- NVIDIA P104-100*
- Type
- GPU*
- Release Date
- 2017-12-12*
- Process Size (nm)
- 16* nm
- Die Size (mm^2)
- 314* mm²
- Transistors (million)
- 7,200*
- Freq (MHz)
- 1,607* MHz
Specifications 2 · 28 fields
- proc transistors
- 7,200 million*
- proc die size
- 314* mm²
- cores
- 1,920*
- sm count
- 15*
- base clock
- 1,607*
- boost clock
- 1,733*
- memory clock
- 1,251*
- ram
- 4*
- name
- NVIDIA P104-100*
- ram type
- GDDR5X*
- bus width
- 256*
- bus interface
- PCIe 1.0 x4*
- ram bandwidth
- 320.3* GB/s
- fp16 performance
- 0.104*
- fp32 performance
- 6.655*
- fp64 performance
- 0.208*
- suggested psu
- 200* W
- slot width
- Dual-slot*
- power connectors
- 1x 8-pin*
- api cuda
- 6.1*
- is retail board
- No*
- gpi value
- 4.68*
- vendor
- nvd*
- manufacturer
- NVIDIA*
- arch name
- Pascal*
- card release date
- 2017-12-12*
- proc foundry
- TSMC*
- proc process size
- 16* nm
Specifications 3 · 36 fields
- CUDA compute capability
- 6.1*
- DirectX / feature level
- 12 (12_1)*
- OpenCL
- 3.0*
- OpenGL
- 4.6*
- Shader model
- 6.8*
- Vulkan
- 1.4*
- Graphics interface
- PCIe 1.0 x4*
- Memory bus
- 256* bit
- Reported shader processors
- 1,920*
- Reported theoretical FP16 peak
- 0.104* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP32 peak
- 6.655* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP64 peak
- 0.208* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Declared L1 cache configuration
- 48 KB (per SM)*
- Declared GPU L2 cache
- 2 MB*
- Reported display outputs
- No outputs*
- Theoretical pixel fill rate
- 110.9 GPixel/s*
- External power connectors
- 1x 8-pin*
- Reported chip die area
- 314 mm²*
- Chip foundry
- TSMC*
- Process node declaration
- 16 nm*
- Transistors
- 7,200 million*
- Graphics processor
- GP104*
- Reported video memory
- 4* GB
- Rated memory bandwidth
- 320.3 GB/s*
- Video memory type
- GDDR5X*
- Raster output units
- 64*
- Reported shading units
- 1,920*
- Card or module format
- Dual-slot*
- Streaming multiprocessors
- 15*
- Suggested system PSU
- 200 W*
- 2:4 tensor sparsity
- No*
- Theoretical texture fill rate
- 208.0 GTexel/s*
- Texture mapping units
- 120*
- GPU cores
- 1,920*
- Video memory
- 4* GB
- Video memory type
- GDDR5X*
Specifications 4 · 3 fields
- Device
- NVIDIA P104-100*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
- OpenCL
- 52,593*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
- Vulkan
- 48,169*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
* Provisional data