NVIDIA GeForce RTX 5070 Ti Mobile vs NVIDIA RTX PRO 6000 Blackwell Server

Comparison of NVIDIA GeForce RTX 5070 Ti Mobile with 12 GB GDDR7 and 6,400 cores vs NVIDIA RTX PRO 6000 Blackwell Server with 96 GB GDDR7 and 24,064 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA GeForce RTX 5070 Ti Mobile

14.5

NVIDIA GeForce RTX 5070 Ti Mobile

14.5
MI250 MI250
Instinct MI300X Instinct MI300X
RX 7900 XTX RX 7900 XTX

NVIDIA RTX PRO 6000 Blackwell Server

NVIDIA RTX PRO 6000 Blackwell Server

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks Additional

Memory

Memory Size

🔥 12 ГБ
96 GB

Memory Type

GDDR7 GDDR7

Memory Bandwidth

608.6 GB/s 1.79 TB/s

Memory Bus Width

192 бит 512 бит

ML Performance

FP16 (Half Precision)

🔥 32.26 TFLOPS
126.0 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 32.26 TFLOPS
126.0 TFLOPS

FP64 (Double Precision)

🔥 +25,609,656% 504,000.0 TFLOPS
1.968 TFLOPS

CUDA Cores

🔥 6,400
24,064

RT Cores

🔥 50
188

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Blackwell 2.0

SM (Streaming Multiprocessor)

🔥 50
188

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

10.1
🔥 12.0

Clocks & Performance

Base Clock

🔥 +41% 2,235
1,590

Boost Clock

🔥 2,520
2,617

Memory Clock

🔥 +14% 2,000
1,750

Power Consumption

TDP/TGP

🔥 -77% 140 W
600 W

Recommended PSU

No 1000 W

Power Connector

None 1x 16-pin

Rendering

Texture Units (TMU)

🔥 200
752

ROP

🔥 50
188

L2 Cache

🔥 40 MB
128 MB

Benchmarks

Hashcat: MD5

90.2 GH/s

Hashcat: SHA-256

11.6 GH/s

Hashcat: SHA-512

4.11 GH/s

Blender: Blend File: Barbershop - Compute: NVIDIA CUDA

78.09 Seconds

Blender: Blend File: Barbershop - Compute: NVIDIA OptiX

46.33 Seconds

Blender: Blend File: Fishy Cat - Compute: NVIDIA CUDA

20.60 Seconds

Blender: Blend File: Fishy Cat - Compute: NVIDIA OptiX

8.45 Seconds

Blender: Blend File: Junkshop - Compute: NVIDIA CUDA

15.22 Seconds

Blender: Blend File: Junkshop - Compute: NVIDIA OptiX

8.28 Seconds

MLPerf, llama2-70b-99.9 (fp4)

3 250 tokens/s

MLPerf, llama3.1-8b (fp4)

5 758 tokens/s

Geekbench AI, FP16

53 322 points

Geekbench AI, INT8

28 264 points

Geekbench AI, FP32

37 299 points

MLPerf, mixtral-8x7b (fp8)

3 767 tokens/s

Additional

Slots

IGP Dual-slot

Release Date

March 13, 2025 March 18, 2025

Display Outputs

1x HDMI 2.1b
3x DisplayPort 2.1a
4x DisplayPort 2.1b

Renting is cheaper than buying