TEST #981 RESULTS
06/03/2025 - 3:24 AM
ACCELERATOR
MODEL
25.1
tokens/s
generation
1.49
sec
time to first token
835
tokens/s
prompt
242
LocalScore
HOW YOU STACK UP
Explore All ResultsFallen Gemma3 27B v1 - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
127.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
969
tokens/s
27.4
tokens/s
1.09
sec
pp4096+tg256
875
tokens/s
24.1
tokens/s
4.72
sec
pp2048+tg256
990
tokens/s
26.3
tokens/s
2.11
sec
pp2048+tg768
977
tokens/s
24.6
tokens/s
2.13
sec
pp1024+tg1024
850
tokens/s
23.6
tokens/s
1.25
sec
pp1280+tg3072
955
tokens/s
23.9
tokens/s
1.38
sec
pp384+tg1152
928
tokens/s
25.3
tokens/s
456
ms
pp64+tg1024
699
tokens/s
25.4
tokens/s
134
ms
pp16+tg1536
272
tokens/s
25.2
tokens/s
96
ms