TEST #418 RESULTS
04/06/2025 - 8:08 PM
ACCELERATOR
MODEL
71.0
tokens/s
generation
1.13
sec
time to first token
1064
tokens/s
prompt
405
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
32GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:16:34 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1299
tokens/s
81.8
tokens/s
800
ms
pp4096+tg256
1115
tokens/s
47.9
tokens/s
3.69
sec
pp2048+tg256
1226
tokens/s
65.4
tokens/s
1.69
sec
pp2048+tg768
1245
tokens/s
62.6
tokens/s
1.66
sec
pp1024+tg1024
1291
tokens/s
74.1
tokens/s
805
ms
pp1280+tg3072
1244
tokens/s
58.4
tokens/s
1.04
sec
pp384+tg1152
1174
tokens/s
80.3
tokens/s
338
ms
pp64+tg1024
768
tokens/s
85.2
tokens/s
94
ms
pp16+tg1536
211
tokens/s
83.5
tokens/s
85
ms