TEST #2779 RESULTS
02/22/2026 - 11:46 AM
ACCELERATOR
MODEL
26.9
tokens/s
generation
563
ms
time to first token
2262
tokens/s
prompt
477
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
60.3GB
OS
Linux
Kernel Release
6.17.0-14-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #14~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Jan 15 15:52:10 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2900
tokens/s
26.9
tokens/s
390
ms
pp4096+tg256
2335
tokens/s
20.8
tokens/s
1.81
sec
pp2048+tg256
2673
tokens/s
26.4
tokens/s
807
ms
pp2048+tg768
2683
tokens/s
25.9
tokens/s
804
ms
pp1024+tg1024
2896
tokens/s
29.0
tokens/s
392
ms
pp1280+tg3072
2696
tokens/s
23.6
tokens/s
510
ms
pp384+tg1152
2882
tokens/s
29.7
tokens/s
168
ms
pp64+tg1024
1004
tokens/s
30.3
tokens/s
95
ms
pp16+tg1536
292
tokens/s
29.9
tokens/s
90
ms