TEST #2086 RESULTS
01/03/2026 - 7:04 PM
ACCELERATOR
MODEL
162
tokens/s
generation
227
ms
time to first token
6037
tokens/s
prompt
1629
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
7614
tokens/s
179
tokens/s
140
ms
pp4096+tg256
4945
tokens/s
142
tokens/s
835
ms
pp2048+tg256
6424
tokens/s
167
tokens/s
325
ms
pp2048+tg768
6416
tokens/s
166
tokens/s
325
ms
pp1024+tg1024
7597
tokens/s
176
tokens/s
140
ms
pp1280+tg3072
7123
tokens/s
156
tokens/s
185
ms
pp384+tg1152
8634
tokens/s
168
tokens/s
50
ms
pp64+tg1024
4350
tokens/s
151
tokens/s
23
ms
pp16+tg1536
1228
tokens/s
157
tokens/s
18
ms