TEST #1987 RESULTS
12/20/2025 - 2:27 PM
ACCELERATOR
MODEL
23.4
tokens/s
generation
2.15
sec
time to first token
600
tokens/s
prompt
187
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600GT with Radeon Graphics (znver3)
RAM
31.1GB
OS
Linux
Kernel Release
6.14.0-116036-tuxedo
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #36~24.04.1tux1 SMP PREEMPT_DYNAMIC Wed Nov 12 16:30:21 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
695
tokens/s
26.6
tokens/s
1.51
sec
pp4096+tg256
584
tokens/s
16.6
tokens/s
7.08
sec
pp2048+tg256
649
tokens/s
21.3
tokens/s
3.20
sec
pp2048+tg768
649
tokens/s
20.4
tokens/s
3.20
sec
pp1024+tg1024
685
tokens/s
25.1
tokens/s
1.53
sec
pp1280+tg3072
675
tokens/s
19.7
tokens/s
1.94
sec
pp384+tg1152
633
tokens/s
26.6
tokens/s
642
ms
pp64+tg1024
595
tokens/s
27.7
tokens/s
142
ms
pp16+tg1536
237
tokens/s
27.0
tokens/s
101
ms