TEST #245 RESULTS
04/04/2025 - 9:36 PM
ACCELERATOR
MODEL
24.6
tokens/s
generation
3.27
sec
time to first token
429
tokens/s
prompt
148
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
8GB
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 21:18:03 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
454
tokens/s
29.4
tokens/s
2.28
sec
pp4096+tg256
364
tokens/s
17.5
tokens/s
11.32
sec
pp2048+tg256
400
tokens/s
22.4
tokens/s
5.16
sec
pp2048+tg768
443
tokens/s
21.7
tokens/s
4.66
sec
pp1024+tg1024
466
tokens/s
24.7
tokens/s
2.23
sec
pp1280+tg3072
470
tokens/s
20.7
tokens/s
2.75
sec
pp384+tg1152
484
tokens/s
27.5
tokens/s
817
ms
pp64+tg1024
595
tokens/s
29.7
tokens/s
124
ms
pp16+tg1536
187
tokens/s
28.3
tokens/s
105
ms