TEST #1386 RESULTS
08/15/2025 - 4:35 PM
ACCELERATOR
MODEL
101
tokens/s
generation
506
ms
time to first token
3088
tokens/s
prompt
851
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
63.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3761
tokens/s
117
tokens/s
281
ms
pp4096+tg256
2028
tokens/s
61.2
tokens/s
2.04
sec
pp2048+tg256
2932
tokens/s
84.2
tokens/s
710
ms
pp2048+tg768
2941
tokens/s
78.8
tokens/s
708
ms
pp1024+tg1024
3752
tokens/s
100
tokens/s
282
ms
pp1280+tg3072
3522
tokens/s
70.0
tokens/s
373
ms
pp384+tg1152
4407
tokens/s
120
tokens/s
101
ms
pp64+tg1024
2875
tokens/s
144
tokens/s
35
ms
pp16+tg1536
1571
tokens/s
132
tokens/s
24
ms