Performance Rating
GALAX RTX 5090 D HOF OC LAB XOC outperforms NVIDIA Tesla T4 by 621.43% in the overall GPU ARK performance rating
NVIDIA Tesla T4
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks AdditionalMemory
Memory Size
+100%
32
ГБ
Memory Type
Memory Bandwidth
1.79 TB/s
Memory Bus Width
ML Performance
FP16 (Half Precision)
+77%
115.5
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+1,319%
115.5
TFLOPS
FP64 (Double Precision)
+610%
1.805
TFLOPS
CUDA Cores
+750%
21,760
RT Cores
+325%
170
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
+325%
170
PCIe Version
ML Software Support
CUDA Version
12.0
Clocks & Performance
Base Clock
+245%
2,017
Boost Clock
+67%
2,655
Memory Clock
+40%
1,750
Power Consumption
TDP/TGP
-88%
70 W
Recommended PSU
-74%
250 W
Power Connector
2x 16-pin
Rendering
Texture Units (TMU)
+325%
680
ROP
+325%
170
L2 Cache
+2,300%
96 MB
Benchmarks
LLM Perf, Llama-2-7b-hf (bnb)
LLM Perf, Llama-2-7b-hf (gptq)
LLM Perf, Llama-2-7b-hf (unquantized)
LLM Perf, Llama-3.1-8B-Instruct (awq)
LLM Perf, Llama-3.1-8B-Instruct (bnb)
LLM Perf, Llama-3.1-8B-Instruct (gptq)
LLM Perf, Meta-Llama-3-8B (awq)
LLM Perf, Meta-Llama-3-8B (bnb)
LLM Perf, Meta-Llama-3-8B (gptq)
LLM Perf, Meta-Llama-3-8B-Instruct (awq)
LLM Perf, Meta-Llama-3-8B-Instruct (bnb)
LLM Perf, Meta-Llama-3-8B-Instruct (gptq)
llama.cpp, llama-2-7b-Q4_0
LLM Perf, Mistral-7B-Instruct-v0.2 (gptq)
LLM Perf, Mistral-7B-v0.1 (bnb)
LLM Perf, Mistral-7B-v0.1 (gptq)
LLM Perf, Mistral-7B-v0.1 (unquantized)
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
