TEST #3646 RESULTS
05/29/2026 - 10:48 AM
ACCELERATOR
MODEL
6.7
tokens/s
generation
10.68
sec
time to first token
129
tokens/s
prompt
43
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D2 16-Core Processor
RAM
60.5GB
OS
Linux
Kernel Release
7.0.2-6-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 7.0.2-6 (2026-05-20T08:55Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
141
tokens/s
6.9
tokens/s
7.39
sec
pp4096+tg256
113
tokens/s
6.3
tokens/s
36.44
sec
pp2048+tg256
130
tokens/s
6.7
tokens/s
15.91
sec
pp2048+tg768
131
tokens/s
6.6
tokens/s
15.84
sec
pp1024+tg1024
140
tokens/s
6.8
tokens/s
7.44
sec
pp1280+tg3072
139
tokens/s
6.5
tokens/s
9.33
sec
pp384+tg1152
146
tokens/s
6.9
tokens/s
2.78
sec
pp64+tg1024
136
tokens/s
7.0
tokens/s
613
ms
pp16+tg1536
87
tokens/s
6.9
tokens/s
325
ms