TEST #3355 RESULTS
04/21/2026 - 3:49 AM
ACCELERATOR
MODEL
66.3
tokens/s
generation
1.54
sec
time to first token
855
tokens/s
prompt
333
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
24GB
OS
Darwin
Kernel Release
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:31:09 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1039
tokens/s
75.2
tokens/s
1000
ms
pp4096+tg256
772
tokens/s
48.1
tokens/s
5.33
sec
pp2048+tg256
912
tokens/s
61.8
tokens/s
2.27
sec
pp2048+tg768
904
tokens/s
60.0
tokens/s
2.28
sec
pp1024+tg1024
968
tokens/s
68.5
tokens/s
1.07
sec
pp1280+tg3072
956
tokens/s
57.0
tokens/s
1.35
sec
pp384+tg1152
995
tokens/s
73.8
tokens/s
402
ms
pp64+tg1024
833
tokens/s
78.4
tokens/s
89
ms
pp16+tg1536
315
tokens/s
74.0
tokens/s
64
ms