TEST #3488 RESULTS
05/10/2026 - 1:43 PM
ACCELERATOR
MODEL
14.2
tokens/s
generation
730
ms
time to first token
1740
tokens/s
prompt
323
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 9600X 6-Core Processor
RAM
30.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2252
tokens/s
15.3
tokens/s
561
ms
pp4096+tg256
1984
tokens/s
13.9
tokens/s
2.14
sec
pp2048+tg256
2164
tokens/s
13.7
tokens/s
1.02
sec
pp2048+tg768
2162
tokens/s
13.2
tokens/s
1.02
sec
pp1024+tg1024
2241
tokens/s
14.4
tokens/s
526
ms
pp1280+tg3072
2089
tokens/s
14.1
tokens/s
684
ms
pp384+tg1152
2076
tokens/s
14.0
tokens/s
262
ms
pp64+tg1024
544
tokens/s
14.2
tokens/s
181
ms
pp16+tg1536
152
tokens/s
14.5
tokens/s
176
ms