TEST #1657 RESULTS
10/16/2025 - 1:12 PM
ACCELERATOR
MODEL
19.5
tokens/s
generation
2.66
sec
time to first token
489
tokens/s
prompt
153
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12700 (alderlake)
RAM
31GB
OS
Linux
Kernel Release
6.14.0-29-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #29~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Aug 14 16:52:50 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
571
tokens/s
21.4
tokens/s
1.84
sec
pp4096+tg256
474
tokens/s
17.4
tokens/s
8.69
sec
pp2048+tg256
516
tokens/s
19.4
tokens/s
4.02
sec
pp2048+tg768
514
tokens/s
18.9
tokens/s
4.04
sec
pp1024+tg1024
546
tokens/s
19.7
tokens/s
1.92
sec
pp1280+tg3072
538
tokens/s
18.1
tokens/s
2.43
sec
pp384+tg1152
593
tokens/s
20.0
tokens/s
696
ms
pp64+tg1024
447
tokens/s
20.4
tokens/s
207
ms
pp16+tg1536
205
tokens/s
20.2
tokens/s
116
ms