TEST #661 RESULTS
04/10/2025 - 12:23 AM
ACCELERATOR
MODEL
153
tokens/s
generation
180
ms
time to first token
7662
tokens/s
prompt
1868
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
15.6GB
OS
Linux
Kernel Release
5.15.167.4-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP Tue Nov 5 00:21:55 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
9619
tokens/s
190
tokens/s
112
ms
pp4096+tg256
6352
tokens/s
138
tokens/s
652
ms
pp2048+tg256
8258
tokens/s
155
tokens/s
256
ms
pp2048+tg768
8537
tokens/s
120
tokens/s
248
ms
pp1024+tg1024
10056
tokens/s
167
tokens/s
110
ms
pp1280+tg3072
9147
tokens/s
117
tokens/s
150
ms
pp384+tg1152
10871
tokens/s
164
tokens/s
40
ms
pp64+tg1024
5331
tokens/s
156
tokens/s
20
ms
pp16+tg1536
783
tokens/s
169
tokens/s
28
ms