TEST #3690 RESULTS
06/06/2026 - 10:19 AM
ACCELERATOR
MODEL
36.1
tokens/s
generation
848
ms
time to first token
1595
tokens/s
prompt
408
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 275HX (arrowlake-s)
RAM
15.5GB
OS
Linux
Kernel Release
6.6.114.1-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Dec 1 20:46:23 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1720
tokens/s
31.2
tokens/s
627
ms
pp4096+tg256
1437
tokens/s
33.6
tokens/s
2.88
sec
pp2048+tg256
1697
tokens/s
36.8
tokens/s
1.24
sec
pp2048+tg768
1732
tokens/s
35.6
tokens/s
1.21
sec
pp1024+tg1024
1908
tokens/s
37.0
tokens/s
564
ms
pp1280+tg3072
1829
tokens/s
38.9
tokens/s
728
ms
pp384+tg1152
2169
tokens/s
37.3
tokens/s
202
ms
pp64+tg1024
1379
tokens/s
37.1
tokens/s
114
ms
pp16+tg1536
480
tokens/s
37.5
tokens/s
59
ms