TEST #1612 RESULTS
10/07/2025 - 10:17 PM
ACCELERATOR
MODEL
98.7
tokens/s
generation
437
ms
time to first token
3114
tokens/s
prompt
889
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 0.5B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-7400 CPU @ 3.00GHz (skylake)
RAM
15.6GB
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
3764
tokens/s
109
tokens/s
281
ms
pp4096+tg256
2640
tokens/s
70.3
tokens/s
1.57
sec
pp2048+tg256
3285
tokens/s
91.4
tokens/s
634
ms
pp2048+tg768
3268
tokens/s
87.9
tokens/s
637
ms
pp1024+tg1024
3734
tokens/s
101
tokens/s
283
ms
pp1280+tg3072
3512
tokens/s
82.4
tokens/s
374
ms
pp384+tg1152
3922
tokens/s
111
tokens/s
106
ms
pp64+tg1024
2845
tokens/s
120
tokens/s
30
ms
pp16+tg1536
1054
tokens/s
115
tokens/s
23
ms