TEST #3494 RESULTS
05/10/2026 - 6:33 PM
ACCELERATOR
MODEL
61.9
tokens/s
generation
636
ms
time to first token
2003
tokens/s
prompt
580
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 7 270K Plus (arrowlake-s)
RAM
15.1GB
OS
Linux
Kernel Release
7.0.3-arch1-2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri, 01 May 2026 15:49:22 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2344
tokens/s
63.8
tokens/s
453
ms
pp4096+tg256
1979
tokens/s
55.5
tokens/s
2.09
sec
pp2048+tg256
2207
tokens/s
60.7
tokens/s
944
ms
pp2048+tg768
2221
tokens/s
60.1
tokens/s
940
ms
pp1024+tg1024
2389
tokens/s
62.8
tokens/s
445
ms
pp1280+tg3072
2309
tokens/s
58.9
tokens/s
570
ms
pp384+tg1152
2321
tokens/s
64.6
tokens/s
191
ms
pp64+tg1024
1727
tokens/s
66.0
tokens/s
51
ms
pp16+tg1536
532
tokens/s
65.0
tokens/s
44
ms