TEST #2060 RESULTS
12/28/2025 - 10:03 PM
ACCELERATOR
MODEL
125
tokens/s
generation
365
ms
time to first token
3784
tokens/s
prompt
1091
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-10750H CPU @ 2.60GHz (skylake)
RAM
15.4GB
OS
Linux
Kernel Release
6.17.9-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon, 24 Nov 2025 15:21:09 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4589
tokens/s
151
tokens/s
230
ms
pp4096+tg256
3048
tokens/s
94.7
tokens/s
1.36
sec
pp2048+tg256
4129
tokens/s
124
tokens/s
505
ms
pp2048+tg768
4153
tokens/s
119
tokens/s
500
ms
pp1024+tg1024
4343
tokens/s
137
tokens/s
244
ms
pp1280+tg3072
4503
tokens/s
105
tokens/s
292
ms
pp384+tg1152
4887
tokens/s
128
tokens/s
85
ms
pp64+tg1024
3931
tokens/s
134
tokens/s
22
ms
pp16+tg1536
474
tokens/s
131
tokens/s
39
ms