TEST #1931 RESULTS
12/12/2025 - 12:32 PM
ACCELERATOR
MODEL
105
tokens/s
generation
208
ms
time to first token
7346
tokens/s
prompt
1545
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
119.7GB
OS
Linux
Kernel Release
6.11.0-1014-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #14-Ubuntu SMP PREEMPT_DYNAMIC Thu Aug 14 18:27:36 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
9168
tokens/s
97.2
tokens/s
123
ms
pp4096+tg256
5149
tokens/s
91.3
tokens/s
809
ms
pp2048+tg256
7252
tokens/s
99.2
tokens/s
295
ms
pp2048+tg768
7299
tokens/s
103
tokens/s
292
ms
pp1024+tg1024
9297
tokens/s
111
tokens/s
119
ms
pp1280+tg3072
8755
tokens/s
104
tokens/s
154
ms
pp384+tg1152
12374
tokens/s
113
tokens/s
41
ms
pp64+tg1024
5048
tokens/s
110
tokens/s
24
ms
pp16+tg1536
1772
tokens/s
112
tokens/s
16
ms