TEST #1572 RESULTS
09/30/2025 - 6:48 AM
ACCELERATOR
MODEL
31.8
tokens/s
generation
6.83
sec
time to first token
216
tokens/s
prompt
100
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11800H @ 2.30GHz (tigerlake)
RAM
31.1GB
OS
Linux
Kernel Release
6.14.0-32-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #32~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Sep 2 14:21:04 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
229
tokens/s
31.3
tokens/s
4.49
sec
pp4096+tg256
173
tokens/s
28.2
tokens/s
23.66
sec
pp2048+tg256
199
tokens/s
31.5
tokens/s
10.33
sec
pp2048+tg768
198
tokens/s
31.1
tokens/s
10.39
sec
pp1024+tg1024
219
tokens/s
32.4
tokens/s
4.70
sec
pp1280+tg3072
219
tokens/s
30.2
tokens/s
5.87
sec
pp384+tg1152
243
tokens/s
33.5
tokens/s
1.61
sec
pp64+tg1024
253
tokens/s
34.1
tokens/s
280
ms
pp16+tg1536
213
tokens/s
33.8
tokens/s
101
ms