TEST #2089 RESULTS
01/03/2026 - 7:19 PM
ACCELERATOR
MODEL
153
tokens/s
generation
231
ms
time to first token
6016
tokens/s
prompt
1587
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
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7577
tokens/s
176
tokens/s
141
ms
pp4096+tg256
4911
tokens/s
143
tokens/s
841
ms
pp2048+tg256
6363
tokens/s
161
tokens/s
328
ms
pp2048+tg768
6379
tokens/s
158
tokens/s
328
ms
pp1024+tg1024
7445
tokens/s
160
tokens/s
144
ms
pp1280+tg3072
6737
tokens/s
138
tokens/s
196
ms
pp384+tg1152
8706
tokens/s
158
tokens/s
54
ms
pp64+tg1024
5022
tokens/s
139
tokens/s
23
ms
pp16+tg1536
1001
tokens/s
148
tokens/s
25
ms