TEST #3053 RESULTS
03/11/2026 - 12:33 AM
ACCELERATOR
MODEL
48.3
tokens/s
generation
1.60
sec
time to first token
774
tokens/s
prompt
286
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
24GB
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
1003
tokens/s
65.2
tokens/s
1.04
sec
pp4096+tg256
732
tokens/s
38.6
tokens/s
5.62
sec
pp2048+tg256
899
tokens/s
52.8
tokens/s
2.30
sec
pp2048+tg768
898
tokens/s
50.7
tokens/s
2.30
sec
pp1024+tg1024
989
tokens/s
59.9
tokens/s
1.05
sec
pp1280+tg3072
976
tokens/s
45.7
tokens/s
1.33
sec
pp384+tg1152
848
tokens/s
49.5
tokens/s
467
ms
pp64+tg1024
473
tokens/s
35.6
tokens/s
153
ms
pp16+tg1536
152
tokens/s
36.6
tokens/s
126
ms