TEST #484 RESULTS
04/07/2025 - 9:50 AM
ACCELERATOR
MODEL
115
tokens/s
generation
115
ms
time to first token
11478
tokens/s
prompt
2256
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9900X 12-Core Processor
RAM
185.8GB
OS
Linux
Kernel Release
6.13.8-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun Mar 23 05:03:09 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
15891
tokens/s
124
tokens/s
73
ms
pp4096+tg256
10873
tokens/s
94.2
tokens/s
388
ms
pp2048+tg256
13834
tokens/s
111
tokens/s
157
ms
pp2048+tg768
13793
tokens/s
107
tokens/s
158
ms
pp1024+tg1024
15662
tokens/s
116
tokens/s
74
ms
pp1280+tg3072
13878
tokens/s
104
tokens/s
101
ms
pp384+tg1152
15055
tokens/s
122
tokens/s
33
ms
pp64+tg1024
2837
tokens/s
128
tokens/s
29
ms
pp16+tg1536
1474
tokens/s
125
tokens/s
17
ms