TEST #3311 RESULTS
04/15/2026 - 6:42 AM
ACCELERATOR
MODEL
58.6
tokens/s
generation
679
ms
time to first token
1878
tokens/s
prompt
545
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i9-12900K (alderlake)
RAM
91.8GB
OS
Linux
Kernel Release
6.8.0-107-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #107-Ubuntu SMP PREEMPT_DYNAMIC Fri Mar 13 19:51:50 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2168
tokens/s
61.4
tokens/s
489
ms
pp4096+tg256
1860
tokens/s
52.8
tokens/s
2.22
sec
pp2048+tg256
2088
tokens/s
58.2
tokens/s
998
ms
pp2048+tg768
2072
tokens/s
57.2
tokens/s
1.01
sec
pp1024+tg1024
2186
tokens/s
59.3
tokens/s
485
ms
pp1280+tg3072
2109
tokens/s
55.2
tokens/s
624
ms
pp384+tg1152
2195
tokens/s
60.5
tokens/s
194
ms
pp64+tg1024
1635
tokens/s
61.7
tokens/s
55
ms
pp16+tg1536
591
tokens/s
60.9
tokens/s
42
ms