TEST #2306 RESULTS
01/15/2026 - 6:40 PM
ACCELERATOR
MODEL
104
tokens/s
generation
159
ms
time to first token
8538
tokens/s
prompt
1775
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 0.6B - Q8_0
SYSTEM
CPU
AMD Ryzen 5 5600 6-Core Processor (znver3)
RAM
31.9GB
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
11681
tokens/s
102
tokens/s
99
ms
pp4096+tg256
7465
tokens/s
103
tokens/s
559
ms
pp2048+tg256
9908
tokens/s
107
tokens/s
218
ms
pp2048+tg768
9759
tokens/s
107
tokens/s
220
ms
pp1024+tg1024
11719
tokens/s
103
tokens/s
98
ms
pp1280+tg3072
10904
tokens/s
105
tokens/s
127
ms
pp384+tg1152
12124
tokens/s
106
tokens/s
42
ms
pp64+tg1024
2670
tokens/s
105
tokens/s
34
ms
pp16+tg1536
610
tokens/s
103
tokens/s
37
ms