TEST #1351 RESULTS
08/09/2025 - 10:52 PM
ACCELERATOR
MODEL
18.5
tokens/s
generation
3.62
sec
time to first token
408
tokens/s
prompt
128
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.8.0-71-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #71-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 16:52:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
474
tokens/s
23.6
tokens/s
2.20
sec
pp4096+tg256
300
tokens/s
2.7
tokens/s
14.01
sec
pp2048+tg256
405
tokens/s
17.3
tokens/s
5.12
sec
pp2048+tg768
407
tokens/s
16.3
tokens/s
5.09
sec
pp1024+tg1024
474
tokens/s
19.9
tokens/s
2.21
sec
pp1280+tg3072
456
tokens/s
10.7
tokens/s
2.86
sec
pp384+tg1152
536
tokens/s
23.6
tokens/s
752
ms
pp64+tg1024
379
tokens/s
26.7
tokens/s
200
ms
pp16+tg1536
244
tokens/s
25.4
tokens/s
97
ms