TEST #902 RESULTS
05/18/2025 - 9:38 PM
ACCELERATOR
MODEL
14.0
tokens/s
generation
24.61
sec
time to first token
61
tokens/s
prompt
33
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3-30B-A3B - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600U with Radeon Graphics (znver3)
RAM
62.1GB
OS
Linux
Kernel Release
6.12.13-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Feb 8 20:05:26 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
64
tokens/s
15.5
tokens/s
15.98
sec
pp4096+tg256
46
tokens/s
10.4
tokens/s
89.79
sec
pp2048+tg256
57
tokens/s
13.6
tokens/s
36.32
sec
pp2048+tg768
56
tokens/s
13.0
tokens/s
36.35
sec
pp1024+tg1024
65
tokens/s
14.4
tokens/s
15.91
sec
pp1280+tg3072
63
tokens/s
12.1
tokens/s
20.45
sec
pp384+tg1152
72
tokens/s
15.4
tokens/s
5.40
sec
pp64+tg1024
72
tokens/s
16.0
tokens/s
946
ms
pp16+tg1536
52
tokens/s
15.6
tokens/s
365
ms