TEST #363 RESULTS
04/06/2025 - 12:22 PM
ACCELERATOR
MODEL
93.5
tokens/s
generation
153
ms
time to first token
8777
tokens/s
prompt
1750
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9554 64-Core Processor (znver4)
RAM
43GB
OS
Linux
Kernel Release
5.15.0-136-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #147-Ubuntu SMP Sat Mar 15 15:53:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11841
tokens/s
98.6
tokens/s
97
ms
pp4096+tg256
7920
tokens/s
76.0
tokens/s
531
ms
pp2048+tg256
10140
tokens/s
90.5
tokens/s
214
ms
pp2048+tg768
10151
tokens/s
87.1
tokens/s
214
ms
pp1024+tg1024
11755
tokens/s
95.0
tokens/s
98
ms
pp1280+tg3072
10588
tokens/s
84.4
tokens/s
132
ms
pp384+tg1152
11920
tokens/s
99.9
tokens/s
42
ms
pp64+tg1024
3456
tokens/s
106
tokens/s
27
ms
pp16+tg1536
1222
tokens/s
104
tokens/s
21
ms