TEST #1093 RESULTS
06/23/2025 - 9:21 AM
ACCELERATOR
MODEL
194
tokens/s
generation
97
ms
time to first token
13974
tokens/s
prompt
3037
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
53.6GB
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
15821
tokens/s
184
tokens/s
70
ms
pp4096+tg256
12560
tokens/s
192
tokens/s
332
ms
pp2048+tg256
16843
tokens/s
198
tokens/s
127
ms
pp2048+tg768
15098
tokens/s
193
tokens/s
141
ms
pp1024+tg1024
19767
tokens/s
199
tokens/s
57
ms
pp1280+tg3072
17497
tokens/s
192
tokens/s
79
ms
pp384+tg1152
20473
tokens/s
199
tokens/s
24
ms
pp64+tg1024
6953
tokens/s
199
tokens/s
14
ms
pp16+tg1536
758
tokens/s
189
tokens/s
26
ms