TEST #1019 RESULTS
06/08/2025 - 11:03 PM
ACCELERATOR
MODEL
43.9
tokens/s
generation
4.16
sec
time to first token
316
tokens/s
prompt
149
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X3D 8-Core Processor (znver3)
RAM
47.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
380
tokens/s
45.8
tokens/s
2.72
sec
pp4096+tg256
280
tokens/s
38.3
tokens/s
14.64
sec
pp2048+tg256
341
tokens/s
43.4
tokens/s
6.03
sec
pp2048+tg768
338
tokens/s
42.5
tokens/s
6.09
sec
pp1024+tg1024
391
tokens/s
44.9
tokens/s
2.65
sec
pp1280+tg3072
384
tokens/s
39.9
tokens/s
3.36
sec
pp384+tg1152
249
tokens/s
45.9
tokens/s
1.56
sec
pp64+tg1024
253
tokens/s
47.8
tokens/s
274
ms
pp16+tg1536
227
tokens/s
46.6
tokens/s
91
ms