TEST #77 RESULTS
03/28/2025 - 9:11 PM
ACCELERATOR
MODEL
144
tokens/s
generation
68
ms
time to first token
19804
tokens/s
prompt
3464
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7950X 16-Core Processor (znver4)
RAM
125GB
OS
Linux
Kernel Release
6.8.0-40-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #40~22.04.3-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 30 17:30:19 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
28215
tokens/s
153
tokens/s
43
ms
pp4096+tg256
18671
tokens/s
125
tokens/s
227
ms
pp2048+tg256
24661
tokens/s
139
tokens/s
90
ms
pp2048+tg768
24608
tokens/s
137
tokens/s
90
ms
pp1024+tg1024
28449
tokens/s
144
tokens/s
43
ms
pp1280+tg3072
19964
tokens/s
134
tokens/s
71
ms
pp384+tg1152
25323
tokens/s
150
tokens/s
22
ms
pp64+tg1024
6512
tokens/s
156
tokens/s
15
ms
pp16+tg1536
1833
tokens/s
154
tokens/s
14
ms