TEST #43 RESULTS
03/28/2025 - 6:54 PM
ACCELERATOR
MODEL
206
tokens/s
generation
238
ms
time to first token
6119
tokens/s
prompt
1743
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7402P 24-Core Processor (znver2)
RAM
251.6GB
OS
Linux
Kernel Release
5.15.0-86-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7612
tokens/s
222
tokens/s
139
ms
pp4096+tg256
4335
tokens/s
166
tokens/s
951
ms
pp2048+tg256
6478
tokens/s
199
tokens/s
321
ms
pp2048+tg768
6476
tokens/s
194
tokens/s
321
ms
pp1024+tg1024
7621
tokens/s
211
tokens/s
139
ms
pp1280+tg3072
7181
tokens/s
187
tokens/s
183
ms
pp384+tg1152
8548
tokens/s
222
tokens/s
49
ms
pp64+tg1024
6124
tokens/s
231
tokens/s
15
ms
pp16+tg1536
694
tokens/s
226
tokens/s
27
ms