TEST #145 RESULTS
03/28/2025 - 10:21 PM
ACCELERATOR
MODEL
52.0
tokens/s
generation
802
ms
time to first token
1595
tokens/s
prompt
470
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.5.0-44-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #44~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jun 18 14:36:16 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2055
tokens/s
56.3
tokens/s
516
ms
pp4096+tg256
1678
tokens/s
47.8
tokens/s
2.46
sec
pp2048+tg256
1727
tokens/s
50.9
tokens/s
1.21
sec
pp2048+tg768
1586
tokens/s
49.7
tokens/s
1.31
sec
pp1024+tg1024
1685
tokens/s
52.3
tokens/s
627
ms
pp1280+tg3072
1755
tokens/s
49.0
tokens/s
748
ms
pp384+tg1152
1875
tokens/s
53.6
tokens/s
235
ms
pp64+tg1024
1520
tokens/s
54.7
tokens/s
60
ms
pp16+tg1536
474
tokens/s
54.1
tokens/s
50
ms