TEST #783 RESULTS
04/29/2025 - 5:57 PM
ACCELERATOR
MODEL
149
tokens/s
generation
906
ms
time to first token
1609
tokens/s
prompt
641
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9454P 48-Core Processor (znver4)
RAM
251.4GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1737
tokens/s
154
tokens/s
596
ms
pp4096+tg256
1245
tokens/s
123
tokens/s
3.30
sec
pp2048+tg256
1554
tokens/s
149
tokens/s
1.32
sec
pp2048+tg768
1554
tokens/s
147
tokens/s
1.32
sec
pp1024+tg1024
1753
tokens/s
151
tokens/s
591
ms
pp1280+tg3072
1732
tokens/s
142
tokens/s
746
ms
pp384+tg1152
1832
tokens/s
155
tokens/s
216
ms
pp64+tg1024
1740
tokens/s
159
tokens/s
43
ms
pp16+tg1536
1331
tokens/s
157
tokens/s
18
ms