GPUs

ATI FireGL V7100 vs NVIDIA RTX 4500 Ada Full Specs

16 Shaders
500MHz
7,680 Shaders
2.58GHz
262MB GDDR328.8GB/s
24GB GDDR6432GB/s
··
-
··
39.63 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
91W
TDP
130W
Power Connectors
-
Power Connectors
1x 16-Pin 12VHPWR

FireGL V7100FireGL V7100-
-
RTX 4500 AdaRTX 4500 Ada1.27 POPSINT4 Tensor Sparse
x1

Clock Speed
··
Clock Speed
···
Peak OPS
-
Peak OPS
1.27 POPSINT4 Tensor Sparse
-
Tensor FP8-16
317 TFLOPS
FP8-16 Tensor Sparse
634.1 TFLOPS
Tensor FP8-32
158.5 TFLOPS
FP8-32 Tensor Sparse
317 TFLOPS
-
Tensor FP16-16
158.5 TFLOPS
FP16-16 Tensor Sparse
317 TFLOPS
Tensor FP16-32
79.26 TFLOPS
FP16-32 Tensor Sparse
158.5 TFLOPS
-
BF16
39.63 TFLOPS
Tensor BF16
79.26 TFLOPS
BF16 Tensor Sparse
158.5 TFLOPS
Tensor TF32
-
Tensor TF32
39.63 TFLOPS
-
FP32
39.63 TFLOPS
-
FP64
619.2 GFLOPS
Tensor INT4
-
Tensor INT4
634.1 TOPS
-
Tensor INT8
317 TOPS
Ray
-
Ray
91.6 TOPS
Pixel Rate
-
Pixel Rate
206.4 GPixel/s
Texture Rate
8 GTexel/s
Texture Rate
619.2 GTexel/s

Shaders
16 Shaders
Shaders
7,680 Shaders
TMUs
16 TMUs
TMUs
240 TMUs
ROPs
-
ROPs
80 ROPs
Tensor Cores
-
Tensor Cores
240 T-Cores
RT Cores
-
RT Cores
60 RT-Cores
Units
-
SMs
60 SMs

Base Clock
-
Base Clock
2.07GHz
Boost Clock
500MHz
Boost Clock
2.58GHz

L2 Cache
-
L2 Cache
49.1MB shared

262MB GDDR3
24GB GDDR6
Memory Bus
256-bit
Memory Bus
192-bit
Memory Speed
900MT/s
Memory Speed
18GT/s
Memory Bandwidth
28.8GB/s
Memory Bandwidth
432GB/s
ECC
-
ECC
Yes

TDP
91W
TDP
130W

Multi-Monitor
2
Multi-Monitor
4
HDCP
-
HDCP
HDCP 2.3

-
4x DisplayPort 1.4
2x DVI-I Dual-Link
-
1x S-Video
-

-
Encoder Model
2x NVENC 8

-
Decoder Model
2x NVDEC 5

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
1-Slots
PCIe
2-Slots
Height
111 mm (4.37")
Width
211 mm (8.31")
Depth
20 mm (0.79")
Height
112 mm (4.41")
Width
245 mm (9.65")
Depth
40 mm (1.57")
Cooling
Blower
1x Fan
Cooling
Passive
-
Power Connectors
-
Power Connectors
1x 16-Pin 12VHPWR

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
FireGL branding
Branding
RTX branding
Codename
Thor
Codename
NV184
Chip Variant
M28 Pro
Chip Variant
AD104-250
Market Segment
Workstation
Market Segment
Workstation
Release Date
Oct 1, 2005
Release Date
Aug 9, 2023

Foundry
TSMC
Foundry
TSMC
Fabrication Node
130nm
Fabrication Node
4N
Die Size
281mm²
Die Size
295mm²
Transistor Count
160 Million
Transistor Count
35.8 Billion
Transistor Density
0.57 MTr/mm²
Transistor Density
121.6 MTr/mm²

No images available
No images available