TEST #1941 RESULTS
12/14/2025 - 11:42 PM
ACCELERATOR
MODEL
111
tokens/s
generation
663
ms
time to first token
1889
tokens/s
prompt
682
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Wed Sep 17 21:41:26 PDT 2025; root:xnu-12377.1.9~141/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2219
tokens/s
128
tokens/s
469
ms
pp4096+tg256
1869
tokens/s
74.4
tokens/s
2.21
sec
pp2048+tg256
2111
tokens/s
101
tokens/s
980
ms
pp2048+tg768
2111
tokens/s
96.4
tokens/s
980
ms
pp1024+tg1024
2215
tokens/s
113
tokens/s
470
ms
pp1280+tg3072
2196
tokens/s
90.7
tokens/s
591
ms
pp384+tg1152
2174
tokens/s
128
tokens/s
184
ms
pp64+tg1024
1575
tokens/s
139
tokens/s
47
ms
pp16+tg1536
534
tokens/s
132
tokens/s
36
ms