TEST #1565 RESULTS
09/26/2025 - 3:08 PM
ACCELERATOR
MODEL
26.1
tokens/s
generation
493
ms
time to first token
2626
tokens/s
prompt
518
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 8945HS w/ Radeon 780M Graphics (znver4)
RAM
30.6GB
OS
Linux
Kernel Release
6.16.3-76061603-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202508231538~1758818838~24.04~0cd02b7 SMP PREEMPT_DYNAMIC Thu S
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3520
tokens/s
29.0
tokens/s
325
ms
pp4096+tg256
2596
tokens/s
16.5
tokens/s
1.64
sec
pp2048+tg256
3147
tokens/s
24.4
tokens/s
692
ms
pp2048+tg768
3140
tokens/s
24.1
tokens/s
693
ms
pp1024+tg1024
3526
tokens/s
27.1
tokens/s
326
ms
pp1280+tg3072
3135
tokens/s
21.5
tokens/s
444
ms
pp384+tg1152
3320
tokens/s
29.8
tokens/s
148
ms
pp64+tg1024
927
tokens/s
31.9
tokens/s
96
ms
pp16+tg1536
319
tokens/s
30.6
tokens/s
77
ms