TEST #1797 RESULTS
11/14/2025 - 10:39 AM
ACCELERATOR
MODEL
62.8
tokens/s
generation
109
ms
time to first token
12461
tokens/s
prompt
1926
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6426Y (sapphirerapids)
RAM
64GB
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
17287
tokens/s
61.4
tokens/s
77
ms
pp4096+tg256
13557
tokens/s
64.1
tokens/s
317
ms
pp2048+tg256
16315
tokens/s
64.2
tokens/s
140
ms
pp2048+tg768
14858
tokens/s
62.1
tokens/s
157
ms
pp1024+tg1024
17207
tokens/s
62.0
tokens/s
76
ms
pp1280+tg3072
15811
tokens/s
61.5
tokens/s
98
ms
pp384+tg1152
14096
tokens/s
63.0
tokens/s
44
ms
pp64+tg1024
2269
tokens/s
63.0
tokens/s
41
ms
pp16+tg1536
752
tokens/s
63.5
tokens/s
34
ms