TEST #135 RESULTS
03/28/2025 - 10:17 PM
ACCELERATOR
MODEL
218
tokens/s
generation
167
ms
time to first token
9134
tokens/s
prompt
2284
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7K62 48-Core Processor (znver2)
RAM
503.5GB
OS
Linux
Kernel Release
5.15.0-122-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #132-Ubuntu SMP Thu Aug 29 13:45:52 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11584
tokens/s
226
tokens/s
93
ms
pp4096+tg256
6286
tokens/s
194
tokens/s
657
ms
pp2048+tg256
8976
tokens/s
213
tokens/s
233
ms
pp2048+tg768
9048
tokens/s
210
tokens/s
231
ms
pp1024+tg1024
11584
tokens/s
220
tokens/s
93
ms
pp1280+tg3072
10901
tokens/s
206
tokens/s
122
ms
pp384+tg1152
14901
tokens/s
226
tokens/s
30
ms
pp64+tg1024
8312
tokens/s
232
tokens/s
12
ms
pp16+tg1536
619
tokens/s
229
tokens/s
30
ms