TEST #3321 RESULTS
04/15/2026 - 10:46 PM
ACCELERATOR
MODEL
58.2
tokens/s
generation
699
ms
time to first token
1821
tokens/s
prompt
533
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
2031
tokens/s
60.5
tokens/s
521
ms
pp4096+tg256
1805
tokens/s
51.8
tokens/s
2.29
sec
pp2048+tg256
2025
tokens/s
57.3
tokens/s
1.03
sec
pp2048+tg768
2029
tokens/s
56.5
tokens/s
1.03
sec
pp1024+tg1024
2162
tokens/s
58.9
tokens/s
490
ms
pp1280+tg3072
2105
tokens/s
55.0
tokens/s
625
ms
pp384+tg1152
2154
tokens/s
60.6
tokens/s
205
ms
pp64+tg1024
1562
tokens/s
61.9
tokens/s
56
ms
pp16+tg1536
518
tokens/s
61.3
tokens/s
46
ms