TEST #339 RESULTS
04/06/2025 - 1:37 AM
ACCELERATOR
MODEL
20.7
tokens/s
generation
1.67
sec
time to first token
832
tokens/s
prompt
218
LocalScore
HOW YOU STACK UP
Explore All ResultsMistral Nemo Instruct 2407 - Q8_0
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
1112
tokens/s
24.9
tokens/s
960
ms
pp4096+tg256
697
tokens/s
4.9
tokens/s
6.07
sec
pp2048+tg256
763
tokens/s
20.7
tokens/s
2.73
sec
pp2048+tg768
953
tokens/s
19.6
tokens/s
2.20
sec
pp1024+tg1024
1095
tokens/s
22.7
tokens/s
975
ms
pp1280+tg3072
1077
tokens/s
14.7
tokens/s
1.23
sec
pp384+tg1152
632
tokens/s
25.1
tokens/s
642
ms
pp64+tg1024
858
tokens/s
27.5
tokens/s
107
ms
pp16+tg1536
300
tokens/s
26.4
tokens/s
85
ms