TEST #1456 RESULTS
08/29/2025 - 9:45 PM
ACCELERATOR
MODEL
21.3
tokens/s
generation
3.89
sec
time to first token
322
tokens/s
prompt
121
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
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:51 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
461
tokens/s
27.3
tokens/s
2.26
sec
pp4096+tg256
344
tokens/s
15.8
tokens/s
11.97
sec
pp2048+tg256
321
tokens/s
18.3
tokens/s
6.44
sec
pp2048+tg768
311
tokens/s
17.1
tokens/s
6.66
sec
pp1024+tg1024
384
tokens/s
21.2
tokens/s
2.71
sec
pp1280+tg3072
368
tokens/s
17.6
tokens/s
3.51
sec
pp384+tg1152
434
tokens/s
24.6
tokens/s
909
ms
pp64+tg1024
164
tokens/s
26.2
tokens/s
413
ms
pp16+tg1536
107
tokens/s
24.0
tokens/s
172
ms