TEST #107 RESULTS
03/28/2025 - 9:45 PM
ACCELERATOR
MODEL
232
tokens/s
generation
159
ms
time to first token
7853
tokens/s
prompt
2252
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
125.6GB
OS
Linux
Kernel Release
5.15.0-124-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #134-Ubuntu SMP Fri Sep 27 20:20:17 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11125
tokens/s
252
tokens/s
96
ms
pp4096+tg256
7373
tokens/s
179
tokens/s
561
ms
pp2048+tg256
9515
tokens/s
218
tokens/s
220
ms
pp2048+tg768
9443
tokens/s
214
tokens/s
221
ms
pp1024+tg1024
10859
tokens/s
239
tokens/s
98
ms
pp1280+tg3072
10176
tokens/s
205
tokens/s
130
ms
pp384+tg1152
9028
tokens/s
255
tokens/s
46
ms
pp64+tg1024
2566
tokens/s
264
tokens/s
29
ms
pp16+tg1536
590
tokens/s
258
tokens/s
31
ms