TEST #1826 RESULTS
11/19/2025 - 12:17 PM
ACCELERATOR
MODEL
135
tokens/s
generation
186
ms
time to first token
7232
tokens/s
prompt
1739
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 5220R CPU @ 2.20GHz (cascadelake)
RAM
63.6GB
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
9641
tokens/s
165
tokens/s
112
ms
pp4096+tg256
6264
tokens/s
160
tokens/s
661
ms
pp2048+tg256
8123
tokens/s
78.8
tokens/s
265
ms
pp2048+tg768
8069
tokens/s
81.0
tokens/s
267
ms
pp1024+tg1024
9523
tokens/s
81.7
tokens/s
120
ms
pp1280+tg3072
8501
tokens/s
162
tokens/s
157
ms
pp384+tg1152
8586
tokens/s
163
tokens/s
52
ms
pp64+tg1024
5422
tokens/s
163
tokens/s
18
ms
pp16+tg1536
964
tokens/s
162
tokens/s
23
ms