TEST #3120 RESULTS
03/19/2026 - 1:26 PM
ACCELERATOR
MODEL
254
tokens/s
generation
87
ms
time to first token
15705
tokens/s
prompt
3576
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 285K (arrowlake-s)
RAM
31GB
OS
Linux
Kernel Release
6.6.87.2-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
21412
tokens/s
266
tokens/s
52
ms
pp4096+tg256
13901
tokens/s
231
tokens/s
299
ms
pp2048+tg256
17942
tokens/s
249
tokens/s
119
ms
pp2048+tg768
13796
tokens/s
235
tokens/s
154
ms
pp1024+tg1024
21965
tokens/s
260
tokens/s
51
ms
pp1280+tg3072
20729
tokens/s
247
tokens/s
66
ms
pp384+tg1152
22650
tokens/s
260
tokens/s
21
ms
pp64+tg1024
6740
tokens/s
271
tokens/s
14
ms
pp16+tg1536
2211
tokens/s
268
tokens/s
11
ms