TEST #1362 RESULTS
08/12/2025 - 3:29 PM
ACCELERATOR
MODEL
117
tokens/s
generation
576
ms
time to first token
2108
tokens/s
prompt
754
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2649
tokens/s
133
tokens/s
394
ms
pp4096+tg256
2163
tokens/s
76.7
tokens/s
1.91
sec
pp2048+tg256
2448
tokens/s
106
tokens/s
846
ms
pp2048+tg768
2457
tokens/s
101
tokens/s
843
ms
pp1024+tg1024
2506
tokens/s
119
tokens/s
417
ms
pp1280+tg3072
2527
tokens/s
94.6
tokens/s
514
ms
pp384+tg1152
2637
tokens/s
135
tokens/s
152
ms
pp64+tg1024
1202
tokens/s
148
tokens/s
59
ms
pp16+tg1536
384
tokens/s
141
tokens/s
47
ms