TEST #1617 RESULTS
10/08/2025 - 1:24 AM
ACCELERATOR
MODEL
63.8
tokens/s
generation
936
ms
time to first token
1520
tokens/s
prompt
470
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 0.5B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-10400 CPU @ 2.90GHz (skylake)
RAM
31.3GB
OS
Linux
Kernel Release
6.8.0-85-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #85-Ubuntu SMP PREEMPT_DYNAMIC Thu Sep 18 15:26:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1770
tokens/s
78.8
tokens/s
591
ms
pp4096+tg256
1200
tokens/s
26.2
tokens/s
3.45
sec
pp2048+tg256
1528
tokens/s
45.9
tokens/s
1.36
sec
pp2048+tg768
1526
tokens/s
41.9
tokens/s
1.36
sec
pp1024+tg1024
1761
tokens/s
59.6
tokens/s
594
ms
pp1280+tg3072
1684
tokens/s
36.9
tokens/s
775
ms
pp384+tg1152
1968
tokens/s
81.8
tokens/s
203
ms
pp64+tg1024
1630
tokens/s
110
tokens/s
44
ms
pp16+tg1536
614
tokens/s
92.7
tokens/s
39
ms