TEST #3074 RESULTS
03/13/2026 - 6:44 PM
ACCELERATOR
MODEL
36.8
tokens/s
generation
925
ms
time to first token
1425
tokens/s
prompt
384
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-9900K CPU @ 3.60GHz (skylake)
RAM
31GB
OS
Linux
Kernel Release
6.8.0-101-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #101-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 9 10:15:05 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1657
tokens/s
40.5
tokens/s
637
ms
pp4096+tg256
1333
tokens/s
34.5
tokens/s
3.10
sec
pp2048+tg256
1522
tokens/s
36.9
tokens/s
1.37
sec
pp2048+tg768
1517
tokens/s
36.2
tokens/s
1.37
sec
pp1024+tg1024
1653
tokens/s
37.0
tokens/s
639
ms
pp1280+tg3072
1585
tokens/s
34.7
tokens/s
827
ms
pp384+tg1152
1619
tokens/s
36.9
tokens/s
270
ms
pp64+tg1024
1480
tokens/s
37.3
tokens/s
60
ms
pp16+tg1536
459
tokens/s
36.9
tokens/s
51
ms