TEST #1716 RESULTS
10/31/2025 - 7:53 AM
ACCELERATOR
MODEL
97.1
tokens/s
generation
1.01
sec
time to first token
1217
tokens/s
prompt
489
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Sep 15 20:25:39 PDT 2025; root:xnu-12377.1.9~126/RELEASE_ARM64_T8142
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1326
tokens/s
106
tokens/s
782
ms
pp4096+tg256
1191
tokens/s
67.4
tokens/s
3.46
sec
pp2048+tg256
1432
tokens/s
90.1
tokens/s
1.44
sec
pp2048+tg768
1418
tokens/s
87.6
tokens/s
1.46
sec
pp1024+tg1024
1509
tokens/s
99.6
tokens/s
688
ms
pp1280+tg3072
1489
tokens/s
83.7
tokens/s
869
ms
pp384+tg1152
1430
tokens/s
110
tokens/s
277
ms
pp64+tg1024
868
tokens/s
117
tokens/s
82
ms
pp16+tg1536
294
tokens/s
112
tokens/s
62
ms