TEST #3039 RESULTS
03/08/2026 - 12:03 AM
ACCELERATOR
MODEL
1.9
tokens/s
generation
23.84
sec
time to first token
57
tokens/s
prompt
17
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 8945HS w/ Radeon 780M Graphics (znver4)
RAM
29.8GB
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
68
tokens/s
2.2
tokens/s
15.57
sec
pp4096+tg256
52
tokens/s
0.4
tokens/s
81.23
sec
pp2048+tg256
61
tokens/s
1.6
tokens/s
34.48
sec
pp2048+tg768
57
tokens/s
1.5
tokens/s
36.35
sec
pp1024+tg1024
70
tokens/s
2.0
tokens/s
15.07
sec
pp1280+tg3072
56
tokens/s
1.0
tokens/s
23.24
sec
pp384+tg1152
72
tokens/s
2.6
tokens/s
5.61
sec
pp64+tg1024
28
tokens/s
3.2
tokens/s
2.48
sec
pp16+tg1536
51
tokens/s
2.9
tokens/s
518
ms