TEST #319 RESULTS
04/06/2025 - 12:13 AM
ACCELERATOR
MODEL
55.5
tokens/s
generation
414
ms
time to first token
3235
tokens/s
prompt
757
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - F16
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
4507
tokens/s
64.8
tokens/s
243
ms
pp4096+tg256
2775
tokens/s
20.6
tokens/s
1.52
sec
pp2048+tg256
3685
tokens/s
54.1
tokens/s
574
ms
pp2048+tg768
3681
tokens/s
52.1
tokens/s
575
ms
pp1024+tg1024
4413
tokens/s
60.1
tokens/s
247
ms
pp1280+tg3072
4079
tokens/s
43.6
tokens/s
330
ms
pp384+tg1152
4509
tokens/s
65.8
tokens/s
99
ms
pp64+tg1024
1169
tokens/s
70.5
tokens/s
68
ms
pp16+tg1536
295
tokens/s
67.7
tokens/s
67
ms