Performance Rating
AMD Radeon Instinct MI325X outperforms MAXSUN RX 480 by 2,064.5% in the overall GPU ARK performance rating
MAXSUN RX 480
Expert Comparison
AMD Radeon Instinct MI325X明显在性能和规格上远超MAXSUN RX 480。MI325X拥有更多的流处理器、更大的显存（288 GB HBM3e vs 8 GB GDDR5）、更高的带宽（10.3 TB/s vs 256 GB/s）以及更高的FP32算力（81.72 TFLOPS vs 5.834 TFLOPS）。它更适合高性能计算任务，如机器学习和大规模数据处理。相比之下，MAXSUN RX 480更适合基本的游戏和图形渲染任务。
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks AdditionalMemory
Memory Size
+3,500%
288
ГБ
Memory Type
Memory Bandwidth
10.3 TB/s
Memory Bus Width
ML Performance
FP16 (Half Precision)
+11,105%
653.7
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+1,301%
81.72
TFLOPS
FP64 (Double Precision)
+22,314%
81.72
TFLOPS
CUDA Cores
+744%
19,456
RT Cores
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
PCIe Version
ML Software Support
CUDA Version
CUDA Toolkit status
Clocks & Performance
Base Clock
1,000
Boost Clock
+66%
2,100
Memory Clock
+26%
2,525
Power Consumption
Recommended PSU
-68%
450 W
Power Connector
TDP/TGP
-85%
150 W
Rendering
Texture Units (TMU)
+744%
1,216
ROP
L2 Cache
+700%
16 MB
Benchmarks
MLPerf, llama2-70b-99.9 (Dummy)
MLPerf, llama2-70b-99.9 (fp8)
llama.cpp, llama-2-7b-Q4_0
MLPerf, mixtral-8x7b (fp8)
Additional
Slots
Release Date
Display Outputs
Renting is cheaper than buying
H100 80Gb SXM (80GB)
NVIDIA
Флагманская GPU на архитектуре Hopper с 80 ГБ памяти HBM3 в форм-факторе SXM. Создана для обучения и инференса больших языковых моделей, HPC задач. Поддерживает FP64, FP32, TF32, FP16, BF16, FP8 и INT8 вычисления с Tensor Cores 4-го поколения.
from 299.11 RUB/hour
