TEST #2987 RESULTS
03/06/2026 - 8:02 AM
ACCELERATOR
MODEL
38.5
tokens/s
generation
2.39
sec
time to first token
544
tokens/s
prompt
206
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jan 19 21:58:37 PST 2026; root:xnu-11417.140.69.708.3~1/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
646
tokens/s
43.5
tokens/s
1.61
sec
pp4096+tg256
488
tokens/s
25.2
tokens/s
8.43
sec
pp2048+tg256
596
tokens/s
34.8
tokens/s
3.47
sec
pp2048+tg768
597
tokens/s
33.1
tokens/s
3.46
sec
pp1024+tg1024
641
tokens/s
39.3
tokens/s
1.62
sec
pp1280+tg3072
634
tokens/s
30.9
tokens/s
2.04
sec
pp384+tg1152
642
tokens/s
45.1
tokens/s
618
ms
pp64+tg1024
471
tokens/s
48.6
tokens/s
154
ms
pp16+tg1536
178
tokens/s
46.2
tokens/s
106
ms