TEST #3414 RESULTS
04/29/2026 - 11:24 AM
ACCELERATOR
MODEL
107
tokens/s
generation
424
ms
time to first token
3289
tokens/s
prompt
940
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-7700T CPU @ 2.90GHz (skylake)
RAM
47.4GB
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
4115
tokens/s
112
tokens/s
257
ms
pp4096+tg256
2604
tokens/s
93.3
tokens/s
1.58
sec
pp2048+tg256
3461
tokens/s
102
tokens/s
601
ms
pp2048+tg768
3454
tokens/s
103
tokens/s
603
ms
pp1024+tg1024
4109
tokens/s
110
tokens/s
259
ms
pp1280+tg3072
3818
tokens/s
101
tokens/s
345
ms
pp384+tg1152
4090
tokens/s
113
tokens/s
105
ms
pp64+tg1024
3350
tokens/s
117
tokens/s
28
ms
pp16+tg1536
601
tokens/s
114
tokens/s
35
ms