TEST #3692 RESULTS
06/06/2026 - 10:31 AM
ACCELERATOR
MODEL
173
tokens/s
generation
114
ms
time to first token
11833
tokens/s
prompt
2613
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 275HX (arrowlake-s)
RAM
15.5GB
OS
Linux
Kernel Release
6.6.114.1-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Dec 1 20:46:23 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
15816
tokens/s
169
tokens/s
72
ms
pp4096+tg256
10193
tokens/s
168
tokens/s
408
ms
pp2048+tg256
13176
tokens/s
171
tokens/s
163
ms
pp2048+tg768
13019
tokens/s
169
tokens/s
163
ms
pp1024+tg1024
15241
tokens/s
171
tokens/s
73
ms
pp1280+tg3072
14423
tokens/s
173
tokens/s
94
ms
pp384+tg1152
16912
tokens/s
176
tokens/s
28
ms
pp64+tg1024
5752
tokens/s
178
tokens/s
17
ms
pp16+tg1536
1968
tokens/s
178
tokens/s
13
ms