TEST #1097 RESULTS
06/24/2025 - 3:55 AM
ACCELERATOR
MODEL
28.6
tokens/s
generation
1.66
sec
time to first token
793
tokens/s
prompt
239
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12700K (alderlake)
RAM
31.1GB
OS
Linux
Kernel Release
6.11.0-26-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #26~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Apr 17 19:20:47 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
917
tokens/s
29.6
tokens/s
1.15
sec
pp4096+tg256
754
tokens/s
25.6
tokens/s
5.47
sec
pp2048+tg256
797
tokens/s
28.4
tokens/s
2.60
sec
pp2048+tg768
858
tokens/s
28.2
tokens/s
2.42
sec
pp1024+tg1024
916
tokens/s
28.8
tokens/s
1.15
sec
pp1280+tg3072
865
tokens/s
27.4
tokens/s
1.51
sec
pp384+tg1152
950
tokens/s
30.5
tokens/s
436
ms
pp64+tg1024
798
tokens/s
28.3
tokens/s
125
ms
pp16+tg1536
281
tokens/s
30.8
tokens/s
87
ms