TEST #3457 RESULTS
05/06/2026 - 9:17 PM
ACCELERATOR
MODEL
36.4
tokens/s
generation
1.20
sec
time to first token
1366
tokens/s
prompt
346
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 5 235 (arrowlake-s)
RAM
62.2GB
OS
Linux
Kernel Release
6.17.0-23-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #23~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 14 16:11:48 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1541
tokens/s
38.2
tokens/s
690
ms
pp4096+tg256
1219
tokens/s
27.6
tokens/s
3.40
sec
pp2048+tg256
1489
tokens/s
34.2
tokens/s
1.41
sec
pp2048+tg768
1487
tokens/s
33.3
tokens/s
1.41
sec
pp1024+tg1024
1677
tokens/s
37.2
tokens/s
637
ms
pp1280+tg3072
1596
tokens/s
31.9
tokens/s
829
ms
pp384+tg1152
1857
tokens/s
40.5
tokens/s
230
ms
pp64+tg1024
1423
tokens/s
42.9
tokens/s
67
ms
pp16+tg1536
7
tokens/s
41.5
tokens/s
2.16
sec