TEST #3986 RESULTS
08/02/2026 - 8:40 PM
ACCELERATOR
MODEL
16.4
tokens/s
generation
4.50
sec
time to first token
337
tokens/s
prompt
107
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Genuine Intel CPU 0000 @ 2.40GHz (skylake)
RAM
15.1GB
OS
Linux
Kernel Release
7.1.3-2-cachyos
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu, 09 Jul 2026 18:16:10 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
377
tokens/s
21.0
tokens/s
2.77
sec
pp4096+tg256
243
tokens/s
2.4
tokens/s
17.27
sec
pp2048+tg256
323
tokens/s
15.5
tokens/s
6.40
sec
pp2048+tg768
323
tokens/s
14.6
tokens/s
6.40
sec
pp1024+tg1024
376
tokens/s
17.8
tokens/s
2.77
sec
pp1280+tg3072
363
tokens/s
9.3
tokens/s
3.57
sec
pp384+tg1152
416
tokens/s
21.0
tokens/s
962
ms
pp64+tg1024
370
tokens/s
23.6
tokens/s
209
ms
pp16+tg1536
238
tokens/s
22.3
tokens/s
102
ms