TEST #702 RESULTS
04/12/2025 - 5:34 PM
ACCELERATOR
MODEL
2.5
tokens/s
generation
4.04
sec
time to first token
368
tokens/s
prompt
61
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 8500G w/ Radeon 740M Graphics (znver4)
RAM
31.1GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
467
tokens/s
2.7
tokens/s
2.56
sec
pp4096+tg256
310
tokens/s
0.8
tokens/s
14.42
sec
pp2048+tg256
395
tokens/s
1.8
tokens/s
5.80
sec
pp2048+tg768
396
tokens/s
1.6
tokens/s
5.80
sec
pp1024+tg1024
460
tokens/s
2.4
tokens/s
2.60
sec
pp1280+tg3072
412
tokens/s
1.4
tokens/s
3.55
sec
pp384+tg1152
506
tokens/s
3.4
tokens/s
968
ms
pp64+tg1024
271
tokens/s
4.6
tokens/s
365
ms
pp16+tg1536
99
tokens/s
3.8
tokens/s
277
ms