TEST #344 RESULTS
04/06/2025 - 2:00 AM
ACCELERATOR
MODEL
27.1
tokens/s
generation
1.90
sec
time to first token
746
tokens/s
prompt
220
LocalScore
HOW YOU STACK UP
Explore All ResultsMistral Nemo Instruct 2407 - Q4_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
847
tokens/s
32.6
tokens/s
1.24
sec
pp4096+tg256
586
tokens/s
5.3
tokens/s
7.17
sec
pp2048+tg256
764
tokens/s
25.7
tokens/s
2.72
sec
pp2048+tg768
770
tokens/s
24.6
tokens/s
2.70
sec
pp1024+tg1024
882
tokens/s
29.6
tokens/s
1.19
sec
pp1280+tg3072
872
tokens/s
17.5
tokens/s
1.50
sec
pp384+tg1152
956
tokens/s
34.0
tokens/s
427
ms
pp64+tg1024
627
tokens/s
38.3
tokens/s
125
ms
pp16+tg1536
411
tokens/s
36.2
tokens/s
61
ms