Samsung RTX 4070 Max-Q

Samsung RTX 4070 Max-Q — 8 Гб GDDR6, 4,608 ядер, GPI 6.2

Loading...

Performance Rating

Samsung RTX 4070 Max-Q содержит 8 Гб видеопамяти GDDR6. Шина 128 бит, пропускная способность 256.0 GB/s. Samsung RTX 4070 Max-Q имеет 4608 CUDA ядер. В карте также есть 36 ядер ускорения трассировки лучей.

Reference card by chip manufacturer: NVIDIA GeForce RTX 4070 Max-Q

A100 A100
H200 H200
MI325X MI325X

Samsung RTX 4070 Max-Q

6.2

Samsung RTX 4070 Max-Q

6.2

Memory

Memory Size

8 GB

Memory Type

Memory Bandwidth

256.0 GB/s

Memory Bus Width

128 бит

ML Performance

FP16 (Half Precision)

11.34 TFLOPS

BF16 (Brain Float)

No TFLOPS
311.84 TFLOPS
(NVIDIA A800 SXM4 80 GB)

TF32 (TensorFloat)

Compute Power

FP32 (Single Precision)

11.34 TFLOPS

FP64 (Double Precision)

0.1771 TFLOPS

CUDA Cores

Architecture & Compatibility

GPU Architecture

Ada Lovelace

SM (Streaming Multiprocessor)

PCIe Version

PCIe 4.0 x8

ML Software Support

CUDA Version

Clocks & Performance

Base Clock

Boost Clock

Memory Clock

Power Consumption

Recommended PSU

Power Connector

None

TDP/TGP

35 W
unknown
(NVIDIA CMP 70HX)

Rendering

Texture Units (TMU)

L2 Cache

32 MB

Additional

Slots

IGP
SXM Module
(NVIDIA B300)

Release Date

Jan. 3, 2023
March 12, 2026
(Intel Arc B770)

Display Outputs

Portable Device Dependent
Portable Device Dependent
(NVIDIA GeForce RTX 5090 Mobile)

Renting is cheaper than buying