TEST #1561 RESULTS
09/26/2025 - 11:52 AM
ACCELERATOR
MODEL
158
tokens/s
generation
1.70
sec
time to first token
21826
tokens/s
prompt
1267
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.8GB
OS
Linux
Kernel Release
6.6.87.2-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
30395
tokens/s
171
tokens/s
40
ms
pp4096+tg256
22014
tokens/s
124
tokens/s
194
ms
pp2048+tg256
28420
tokens/s
154
tokens/s
79
ms
pp2048+tg768
28831
tokens/s
150
tokens/s
78
ms
pp1024+tg1024
31637
tokens/s
164
tokens/s
38
ms
pp1280+tg3072
26195
tokens/s
143
tokens/s
56
ms
pp384+tg1152
24091
tokens/s
173
tokens/s
22
ms
pp64+tg1024
4850
tokens/s
175
tokens/s
19
ms
pp16+tg1536
1
tokens/s
174
tokens/s
14.77
sec