TEST #3587 RESULTS
05/21/2026 - 11:23 AM
ACCELERATOR
MODEL
39.4
tokens/s
generation
899
ms
time to first token
1493
tokens/s
prompt
403
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-14700KF (alderlake)
RAM
61.6GB
OS
Linux
Kernel Release
7.0.0-15-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #15-Ubuntu SMP PREEMPT_DYNAMIC Wed Apr 22 16:06:43 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1655
tokens/s
40.2
tokens/s
643
ms
pp4096+tg256
1353
tokens/s
35.3
tokens/s
3.06
sec
pp2048+tg256
1587
tokens/s
38.2
tokens/s
1.32
sec
pp2048+tg768
1590
tokens/s
38.0
tokens/s
1.31
sec
pp1024+tg1024
1749
tokens/s
39.8
tokens/s
610
ms
pp1280+tg3072
1695
tokens/s
37.9
tokens/s
780
ms
pp384+tg1152
1935
tokens/s
41.4
tokens/s
222
ms
pp64+tg1024
1330
tokens/s
42.2
tokens/s
99
ms
pp16+tg1536
542
tokens/s
41.6
tokens/s
53
ms