TEST #41 RESULTS
03/28/2025 - 6:25 PM
ACCELERATOR
MODEL
76.4
tokens/s
generation
1.19
sec
time to first token
1103
tokens/s
prompt
414
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
24.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.1.0: Thu Oct 10 21:06:23 PDT 2024; root:xnu-11215.41.3~3/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1330
tokens/s
84.4
tokens/s
782
ms
pp4096+tg256
977
tokens/s
55.2
tokens/s
4.21
sec
pp2048+tg256
1198
tokens/s
70.9
tokens/s
1.72
sec
pp2048+tg768
1198
tokens/s
68.6
tokens/s
1.72
sec
pp1024+tg1024
1318
tokens/s
78.1
tokens/s
789
ms
pp1280+tg3072
1298
tokens/s
65.0
tokens/s
999
ms
pp384+tg1152
1326
tokens/s
85.8
tokens/s
301
ms
pp64+tg1024
934
tokens/s
91.5
tokens/s
79
ms
pp16+tg1536
349
tokens/s
88.2
tokens/s
57
ms