TEST #481 RESULTS
04/07/2025 - 9:29 AM
ACCELERATOR
MODEL
238
tokens/s
generation
106
ms
time to first token
13799
tokens/s
prompt
3138
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-13600K (alderlake)
RAM
31.8GB
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
17582
tokens/s
237
tokens/s
62
ms
pp4096+tg256
9952
tokens/s
217
tokens/s
416
ms
pp2048+tg256
14037
tokens/s
241
tokens/s
150
ms
pp2048+tg768
14310
tokens/s
240
tokens/s
147
ms
pp1024+tg1024
18734
tokens/s
237
tokens/s
59
ms
pp1280+tg3072
17782
tokens/s
227
tokens/s
76
ms
pp384+tg1152
21903
tokens/s
248
tokens/s
22
ms
pp64+tg1024
7697
tokens/s
248
tokens/s
12
ms
pp16+tg1536
2194
tokens/s
249
tokens/s
12
ms