TEST #3425 RESULTS
05/02/2026 - 12:35 PM
ACCELERATOR
MODEL
37.3
tokens/s
generation
2.52
sec
time to first token
509
tokens/s
prompt
196
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
8GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:34 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
639
tokens/s
44.4
tokens/s
1.63
sec
pp4096+tg256
485
tokens/s
24.4
tokens/s
8.48
sec
pp2048+tg256
513
tokens/s
33.1
tokens/s
4.02
sec
pp2048+tg768
556
tokens/s
31.4
tokens/s
3.71
sec
pp1024+tg1024
592
tokens/s
37.9
tokens/s
1.75
sec
pp1280+tg3072
610
tokens/s
28.7
tokens/s
2.12
sec
pp384+tg1152
623
tokens/s
44.1
tokens/s
637
ms
pp64+tg1024
409
tokens/s
48.0
tokens/s
175
ms
pp16+tg1536
158
tokens/s
43.4
tokens/s
122
ms