TEST #321 RESULTS
04/06/2025 - 12:17 AM
ACCELERATOR
MODEL
103
tokens/s
generation
259
ms
time to first token
6338
tokens/s
prompt
1359
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q8_0
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
125.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8397
tokens/s
127
tokens/s
130
ms
pp4096+tg256
3857
tokens/s
24.1
tokens/s
1.10
sec
pp2048+tg256
5922
tokens/s
91.9
tokens/s
357
ms
pp2048+tg768
5917
tokens/s
86.5
tokens/s
357
ms
pp1024+tg1024
8035
tokens/s
112
tokens/s
135
ms
pp1280+tg3072
7726
tokens/s
65.0
tokens/s
174
ms
pp384+tg1152
10129
tokens/s
130
tokens/s
44
ms
pp64+tg1024
5148
tokens/s
149
tokens/s
18
ms
pp16+tg1536
1911
tokens/s
138
tokens/s
14
ms