TEST #3130 RESULTS
03/20/2026 - 1:26 PM
ACCELERATOR
MODEL
60.0
tokens/s
generation
1.55
sec
time to first token
846
tokens/s
prompt
320
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
8GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:56:34 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1011
tokens/s
67.6
tokens/s
1.03
sec
pp4096+tg256
743
tokens/s
39.2
tokens/s
5.54
sec
pp2048+tg256
915
tokens/s
53.7
tokens/s
2.26
sec
pp2048+tg768
920
tokens/s
51.6
tokens/s
2.25
sec
pp1024+tg1024
1006
tokens/s
61.1
tokens/s
1.03
sec
pp1280+tg3072
987
tokens/s
48.5
tokens/s
1.31
sec
pp384+tg1152
1009
tokens/s
69.5
tokens/s
393
ms
pp64+tg1024
758
tokens/s
76.3
tokens/s
96
ms
pp16+tg1536
270
tokens/s
72.2
tokens/s
71
ms