FireGL V8650 vs H200 NVL
We compared two Desktop platform GPUs: 2GB VRAM FireGL V8650 and 141GB VRAM H200 NVL to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
H200 NVL 's Advantages
Released 17 years and 3 months late
Boost Clock1785MHz
More VRAM (141GB vs 2GB)
Larger VRAM bandwidth (4.89TB/s vs 111.1GB/s)
16576 additional rendering cores
Score
Benchmark
FP32 (float)
FireGL V8650
440
H200 NVL
+13609%
60320
Graphics Card
Aug 2007
Release Date
Nov 2024
FireGL
Generation
Server Hopper
Desktop
Type
Desktop
PCIe 1.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
-
Base Clock
1365 MHz
-
Boost Clock
1785 MHz
868 MHz
Memory Clock
1593 MHz
Memory
2GB
Memory Size
141GB
GDDR4
Memory Type
HBM3e
512bit
Memory Bus
6144bit
111.1GB/s
Bandwidth
4.89TB/s
Render Config
4
Compute Units
-
-
SM Count
132
320
Shading Units
16896
16
TMUs
528
16
ROPs
24
-
Tensor Cores
528
-
L1 Cache
256 KB (per SM)
256 KB
L2 Cache
50 MB
Theoretical Performance
11.01 GPixel/s
Pixel Rate
42.84 GPixel/s
11.01 GTexel/s
Texture Rate
942.5 GTexel/s
-
FP16 (half)
241.3 TFLOPS
440.3 GFLOPS
FP32 (float)
60.32 TFLOPS
-
FP64 (double)
30.16 TFLOPS
Board Design
Unknown
TDP
600W
200 W
Suggested PSU
1000 W
2x DVI
1x S-Video
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
R600
GPU Name
GH100
R600 V8650
(215RGIDKA13FG)
GPU Variant
-
TeraScale
Architecture
Hopper
TSMC
Foundry
TSMC
80 nm
Process Size
5 nm
0.72 billion
Transistors
80 billion
420 mm²
Die Size
814 mm²
Graphics Features
10.0 (10_0)
DirectX
N/A
3.3 (full)
4.0 (partial)
OpenGL
N/A
N/A
OpenCL
3.0
N/A
Vulkan
N/A
-
CUDA
9.0
4.0
Shader Model
N/A
