TEST #3455 RESULTS
05/06/2026 - 7:03 PM
ACCELERATOR
MODEL
42.4
tokens/s
generation
3.93
sec
time to first token
369
tokens/s
prompt
158
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
31.9GB
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
407
tokens/s
48.7
tokens/s
2.54
sec
pp4096+tg256
290
tokens/s
37.0
tokens/s
14.13
sec
pp2048+tg256
353
tokens/s
41.6
tokens/s
5.83
sec
pp2048+tg768
355
tokens/s
40.7
tokens/s
5.79
sec
pp1024+tg1024
387
tokens/s
42.6
tokens/s
2.67
sec
pp1280+tg3072
395
tokens/s
39.2
tokens/s
3.26
sec
pp384+tg1152
418
tokens/s
43.9
tokens/s
940
ms
pp64+tg1024
402
tokens/s
44.5
tokens/s
181
ms
pp16+tg1536
314
tokens/s
43.8
tokens/s
71
ms