Report an Error

NVIDIA GF104

Default
GF104
GF104-300-KA-A1
GF104-300-KA-A1
N12E-GTX-A1
N12E-GTX-A1
N12E-Q1-A1
N12E-Q1-A1
N12E-Q3-A1
N12E-Q3-A1
Block Diagram
Block Diagram
SM Diagram
SM Diagram
NVIDIA's GF104 GPU uses the Fermi architecture and is made using a 40 nm production process at TSMC. With a die size of 332 mm² and a transistor count of 1,950 million it is a large chip. GF104 supports DirectX 12 (Feature Level 11_0). For GPU compute applications, OpenCL version 1.1 and CUDA 2.1 can be used. It features 384 shading units, 64 texture mapping units and 32 ROPs.
Further reading: Fermi Compute Architecture

Graphics Processor

Released
Jul 12th, 2010
GPU Name
GF104
Codename
NVC4
Architecture
Fermi
Foundry
TSMC
Process Size
40 nm
Transistors
1,950 million
Density
5.9M / mm²
Die Size
332 mm²
Package
BGA-1724

Graphics Features

DirectX
12 (11_0)
OpenGL
4.6
OpenCL
1.1
Vulkan
N/A
CUDA
2.1
Shader Model
5.1
WDDM
2.3
PureVideo HD
VP4
VDPAU
Feature Set C

Render Config

Shading Units
384
TMUs
64
ROPs
32
SM Count
8
SFUs
64
GPCs
2
L1 Cache
64 KB per SM
L2 Cache
512 KB
Max. TDP
160 W

All Fermi GPUs

NVIDIA GPU Architecture History

Graphics cards using the NVIDIA GF104 GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Memory Clock
NVIDIA GeForce GTX 460
GF104-325-A1 1024 MB 336 56 32 675 MHz 900 MHz
NVIDIA GeForce GTX 460 SE
GF104-225-A1 1024 MB 288 48 32 650 MHz 850 MHz
NVIDIA GeForce GTX 485M
N12E-GTX-A1 2 GB 384 64 32 575 MHz 750 MHz
NVIDIA Quadro 4000M
N12E-Q3-A1 2 GB 336 56 32 475 MHz 625 MHz
NVIDIA Quadro 3000M
N12E-Q1-A1 2 GB 240 40 32 450 MHz 625 MHz
NVIDIA GeForce GTX 470M
N11E-GT 1536 MB 288 48 24 535 MHz 750 MHz
NVIDIA GeForce GTX 460 OEM
GF104-325-A1 1024 MB 336 56 32 650 MHz 850 MHz
NVIDIA GeForce GTX 460 X2
GF104-300-KB-A1 1024 MB 336 56 32 701 MHz 900 MHz
NVIDIA GeForce GTX 460
GF104-300-KB-A1 768 MB 336 56 24 675 MHz 900 MHz

GF104 GPU Notes

PureVideo HD: VP4
VDPAU: Feature Set C
May 21st, 2024 13:59 EDT change timezone

Latest GPU Drivers

New Forum Posts

Popular Reviews

Controversial News Posts