TEST #425 RESULTS
04/06/2025 - 9:12 PM
ACCELERATOR
MODEL
40.6
tokens/s
generation
5.33
sec
time to first token
280
tokens/s
prompt
129
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 3700X 8-Core Processor (znver2)
RAM
31.3GB
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
281
tokens/s
43.1
tokens/s
3.68
sec
pp4096+tg256
222
tokens/s
34.9
tokens/s
18.45
sec
pp2048+tg256
258
tokens/s
39.8
tokens/s
7.95
sec
pp2048+tg768
259
tokens/s
39.1
tokens/s
7.93
sec
pp1024+tg1024
281
tokens/s
41.4
tokens/s
3.68
sec
pp1280+tg3072
277
tokens/s
37.9
tokens/s
4.65
sec
pp384+tg1152
303
tokens/s
42.9
tokens/s
1.30
sec
pp64+tg1024
319
tokens/s
43.2
tokens/s
217
ms
pp16+tg1536
321
tokens/s
42.7
tokens/s
80
ms