TEST #3163 RESULTS
03/23/2026 - 12:57 PM
ACCELERATOR
MODEL
97.8
tokens/s
generation
995
ms
time to first token
1283
tokens/s
prompt
501
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 4P+6E
RAM
32GB
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 20:56:42 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T8142
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1525
tokens/s
109
tokens/s
681
ms
pp4096+tg256
1214
tokens/s
70.7
tokens/s
3.39
sec
pp2048+tg256
1409
tokens/s
91.0
tokens/s
1.46
sec
pp2048+tg768
1406
tokens/s
87.7
tokens/s
1.47
sec
pp1024+tg1024
1474
tokens/s
99.6
tokens/s
704
ms
pp1280+tg3072
1485
tokens/s
83.3
tokens/s
871
ms
pp384+tg1152
1495
tokens/s
110
tokens/s
265
ms
pp64+tg1024
1124
tokens/s
117
tokens/s
66
ms
pp16+tg1536
413
tokens/s
113
tokens/s
47
ms