TEST #415 RESULTS
04/06/2025 - 7:45 PM
ACCELERATOR
MODEL
67.8
tokens/s
generation
1.41
sec
time to first token
937
tokens/s
prompt
356
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:23 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1126
tokens/s
75.7
tokens/s
923
ms
pp4096+tg256
814
tokens/s
48.4
tokens/s
5.05
sec
pp2048+tg256
1008
tokens/s
62.5
tokens/s
2.05
sec
pp2048+tg768
1000
tokens/s
59.8
tokens/s
2.06
sec
pp1024+tg1024
1118
tokens/s
69.5
tokens/s
929
ms
pp1280+tg3072
1093
tokens/s
57.9
tokens/s
1.19
sec
pp384+tg1152
1141
tokens/s
75.9
tokens/s
348
ms
pp64+tg1024
820
tokens/s
81.4
tokens/s
90
ms
pp16+tg1536
317
tokens/s
78.9
tokens/s
62
ms