TEST #531 RESULTS
04/07/2025 - 9:28 PM
ACCELERATOR
MODEL
282
tokens/s
generation
56
ms
time to first token
25807
tokens/s
prompt
5079
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700K (alderlake)
RAM
63.8GB
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
33509
tokens/s
282
tokens/s
34
ms
pp4096+tg256
19970
tokens/s
264
tokens/s
209
ms
pp2048+tg256
28609
tokens/s
280
tokens/s
75
ms
pp2048+tg768
28298
tokens/s
281
tokens/s
76
ms
pp1024+tg1024
36398
tokens/s
279
tokens/s
32
ms
pp1280+tg3072
33993
tokens/s
280
tokens/s
41
ms
pp384+tg1152
37685
tokens/s
287
tokens/s
13
ms
pp64+tg1024
10870
tokens/s
296
tokens/s
11
ms
pp16+tg1536
2931
tokens/s
292
tokens/s
9
ms