Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

Version 1 Next »

Benchmark Question:
Prompt: 7000 tokens
Completion: 214 tokens

GPU

vRAM

Answer Speed

4 questions

Price

AWS*

Runpod*

L4

24

16

37

G6 $0.80

$0.43

4090

24

5

8

$2,000

NA

$0.69

L40s

48

6.5

9

$9,800

G6e $1.861

$1.03

H100 SXM

80

2.4

3.4

$31,000

NA

$2.99

* Discounts available for different usage patterns

  • No labels