TEST #3607 RESULTS
05/25/2026 - 1:59 PM
ACCELERATOR
MODEL
92.6
tokens/s
generation
803
ms
time to first token
1638
tokens/s
prompt
574
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Pro 6P+6E
RAM
18GB
OS
Darwin
Kernel Release
25.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.5.0: Mon Apr 27 20:41:06 PDT 2026; root:xnu-12377.121.6~2/RELEASE_ARM64_T6030
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2020
tokens/s
106
tokens/s
516
ms
pp4096+tg256
1422
tokens/s
65.7
tokens/s
2.90
sec
pp2048+tg256
1800
tokens/s
86.7
tokens/s
1.15
sec
pp2048+tg768
1807
tokens/s
83.1
tokens/s
1.15
sec
pp1024+tg1024
1947
tokens/s
91.9
tokens/s
536
ms
pp1280+tg3072
1893
tokens/s
76.3
tokens/s
687
ms
pp384+tg1152
1993
tokens/s
103
tokens/s
201
ms
pp64+tg1024
1388
tokens/s
111
tokens/s
54
ms
pp16+tg1536
473
tokens/s
109
tokens/s
42
ms