Performance Rating
AMD Radeon Instinct MI325X outperforms AMD Radeon RX 9060 XT LP by 784.17% in the overall GPU ARK performance rating
AMD Radeon RX 9060 XT LP
The AMD Radeon Instinct MI325X dramatically outperforms the AMD Radeon RX 9060 XT LP, leading by 784% in the overall GPI performance index. For machine learning, the AMD Radeon Instinct MI325X has the edge in VRAM (288 vs 16 GB) and FP16 performance (+1175%). For gaming, the AMD Radeon Instinct MI325X delivers 219% more FP32 throughput, and the AMD Radeon RX 9060 XT LP supports hardware ray tracing. In performance per watt, the AMD Radeon RX 9060 XT LP is 124% more efficient at 140W TDP vs 1000W for the AMD Radeon Instinct MI325X.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks AdditionalMemory
Memory Size
+1,700%
288
ГБ
Memory Type
Memory Bandwidth
10.3 TB/s
Memory Bus Width
ML Performance
FP16 (Half Precision)
+1,175%
653.7
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+219%
81.72
TFLOPS
FP64 (Double Precision)
+10,098%
81.72
TFLOPS
CUDA Cores
+850%
19,456
RT Cores
32
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
PCIe Version
ML Software Support
CUDA Version
Clocks & Performance
Base Clock
+70%
1,700
Boost Clock
+49%
3,130
Memory Clock
2,525
Power Consumption
Recommended PSU
-79%
300 W
Power Connector
TDP/TGP
-86%
140 W
Rendering
Texture Units (TMU)
+850%
1,216
ROP
32
L2 Cache
4 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
