TEST #342 RESULTS
04/06/2025 - 1:53 AM
ACCELERATOR
MODEL
25.3
tokens/s
generation
1.87
sec
time to first token
717
tokens/s
prompt
213
LocalScore
HOW YOU STACK UP
Explore All ResultsMistral Nemo Instruct 2407 - Q5_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
125.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
934
tokens/s
31.0
tokens/s
1.13
sec
pp4096+tg256
623
tokens/s
5.0
tokens/s
6.76
sec
pp2048+tg256
699
tokens/s
24.5
tokens/s
2.97
sec
pp2048+tg768
822
tokens/s
23.3
tokens/s
2.53
sec
pp1024+tg1024
931
tokens/s
27.7
tokens/s
1.13
sec
pp1280+tg3072
910
tokens/s
16.5
tokens/s
1.44
sec
pp384+tg1152
575
tokens/s
31.6
tokens/s
695
ms
pp64+tg1024
643
tokens/s
35.2
tokens/s
125
ms
pp16+tg1536
316
tokens/s
33.4
tokens/s
75
ms