TEST #323 RESULTS
04/06/2025 - 12:21 AM
ACCELERATOR
MODEL
110
tokens/s
generation
281
ms
time to first token
5591
tokens/s
prompt
1299
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q5_K - Medium
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
7359
tokens/s
137
tokens/s
147
ms
pp4096+tg256
3612
tokens/s
24.4
tokens/s
1.17
sec
pp2048+tg256
5377
tokens/s
96.7
tokens/s
391
ms
pp2048+tg768
5385
tokens/s
90.7
tokens/s
390
ms
pp1024+tg1024
7079
tokens/s
118
tokens/s
152
ms
pp1280+tg3072
6838
tokens/s
67.5
tokens/s
195
ms
pp384+tg1152
8571
tokens/s
143
tokens/s
50
ms
pp64+tg1024
4171
tokens/s
164
tokens/s
20
ms
pp16+tg1536
1926
tokens/s
151
tokens/s
13
ms