TEST #596 RESULTS
04/08/2025 - 12:23 PM
ACCELERATOR
MODEL
67.7
tokens/s
generation
1.41
sec
time to first token
938
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
24GB
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 21:18:00 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1129
tokens/s
75.9
tokens/s
920
ms
pp4096+tg256
819
tokens/s
48.2
tokens/s
5.02
sec
pp2048+tg256
1014
tokens/s
62.6
tokens/s
2.03
sec
pp2048+tg768
1010
tokens/s
59.4
tokens/s
2.04
sec
pp1024+tg1024
1108
tokens/s
68.8
tokens/s
938
ms
pp1280+tg3072
1100
tokens/s
57.3
tokens/s
1.18
sec
pp384+tg1152
1142
tokens/s
76.6
tokens/s
348
ms
pp64+tg1024
883
tokens/s
81.7
tokens/s
84
ms
pp16+tg1536
239
tokens/s
79.2
tokens/s
78
ms