TEST #1879 RESULTS
11/28/2025 - 1:13 PM
ACCELERATOR
MODEL
218
tokens/s
generation
109
ms
time to first token
13459
tokens/s
prompt
3000
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i9-12900KS (alderlake)
RAM
31.7GB
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
14834
tokens/s
211
tokens/s
74
ms
pp4096+tg256
9758
tokens/s
213
tokens/s
426
ms
pp2048+tg256
14369
tokens/s
225
tokens/s
147
ms
pp2048+tg768
14449
tokens/s
227
tokens/s
146
ms
pp1024+tg1024
18612
tokens/s
222
tokens/s
60
ms
pp1280+tg3072
17397
tokens/s
189
tokens/s
78
ms
pp384+tg1152
22672
tokens/s
223
tokens/s
22
ms
pp64+tg1024
6595
tokens/s
229
tokens/s
14
ms
pp16+tg1536
2441
tokens/s
228
tokens/s
12
ms