TEST #315 RESULTS
04/05/2025 - 11:46 PM
ACCELERATOR
MODEL
138
tokens/s
generation
105
ms
time to first token
12894
tokens/s
prompt
2574
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7950X3D 16-Core Processor (znver4)
RAM
61.9GB
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
16799
tokens/s
155
tokens/s
67
ms
pp4096+tg256
11514
tokens/s
112
tokens/s
365
ms
pp2048+tg256
14701
tokens/s
133
tokens/s
147
ms
pp2048+tg768
14717
tokens/s
129
tokens/s
147
ms
pp1024+tg1024
17040
tokens/s
141
tokens/s
67
ms
pp1280+tg3072
15831
tokens/s
124
tokens/s
88
ms
pp384+tg1152
18358
tokens/s
148
tokens/s
28
ms
pp64+tg1024
5523
tokens/s
152
tokens/s
18
ms
pp16+tg1536
1566
tokens/s
150
tokens/s
16
ms