TEST #858 RESULTS
05/11/2025 - 5:36 PM
ACCELERATOR
MODEL
136
tokens/s
generation
276
ms
time to first token
4902
tokens/s
prompt
1340
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11800H @ 2.30GHz (tigerlake)
RAM
15.8GB
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
6268
tokens/s
145
tokens/s
170
ms
pp4096+tg256
4103
tokens/s
117
tokens/s
1.01
sec
pp2048+tg256
5282
tokens/s
136
tokens/s
395
ms
pp2048+tg768
5328
tokens/s
132
tokens/s
391
ms
pp1024+tg1024
6234
tokens/s
139
tokens/s
172
ms
pp1280+tg3072
5852
tokens/s
127
tokens/s
226
ms
pp384+tg1152
7234
tokens/s
142
tokens/s
60
ms
pp64+tg1024
3353
tokens/s
142
tokens/s
25
ms
pp16+tg1536
467
tokens/s
142
tokens/s
43
ms