TEST #2809 RESULTS
02/23/2026 - 10:14 AM
ACCELERATOR
MODEL
19.0
tokens/s
generation
1.18
sec
time to first token
1151
tokens/s
prompt
265
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
119.6GB
OS
Linux
Kernel Release
6.17.0-1008-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #8-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 21 17:56:56 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1433
tokens/s
19.5
tokens/s
768
ms
pp4096+tg256
992
tokens/s
17.3
tokens/s
4.19
sec
pp2048+tg256
1260
tokens/s
18.8
tokens/s
1.68
sec
pp2048+tg768
1265
tokens/s
18.7
tokens/s
1.68
sec
pp1024+tg1024
1431
tokens/s
19.4
tokens/s
769
ms
pp1280+tg3072
1380
tokens/s
18.2
tokens/s
981
ms
pp384+tg1152
1558
tokens/s
19.7
tokens/s
298
ms
pp64+tg1024
849
tokens/s
20.0
tokens/s
153
ms
pp16+tg1536
192
tokens/s
19.8
tokens/s
134
ms