TEST #1732 RESULTS
11/05/2025 - 4:55 AM
ACCELERATOR
MODEL
7.7
tokens/s
generation
17.68
sec
time to first token
69
tokens/s
prompt
31
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9900X 12-Core Processor
RAM
31.1GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
95
tokens/s
8.7
tokens/s
10.92
sec
pp4096+tg256
84
tokens/s
7.9
tokens/s
49.10
sec
pp2048+tg256
88
tokens/s
8.3
tokens/s
23.30
sec
pp2048+tg768
92
tokens/s
7.8
tokens/s
22.37
sec
pp1024+tg1024
52
tokens/s
7.3
tokens/s
19.69
sec
pp1280+tg3072
52
tokens/s
7.0
tokens/s
24.63
sec
pp384+tg1152
54
tokens/s
7.4
tokens/s
7.31
sec
pp64+tg1024
54
tokens/s
7.5
tokens/s
1.32
sec
pp16+tg1536
49
tokens/s
7.5
tokens/s
453
ms