TEST #708 RESULTS
04/14/2025 - 1:55 AM
ACCELERATOR
MODEL
75.9
tokens/s
generation
1.19
sec
time to first token
1116
tokens/s
prompt
415
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
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:11:02 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1328
tokens/s
84.0
tokens/s
783
ms
pp4096+tg256
970
tokens/s
54.8
tokens/s
4.24
sec
pp2048+tg256
1202
tokens/s
70.2
tokens/s
1.72
sec
pp2048+tg768
1196
tokens/s
68.0
tokens/s
1.73
sec
pp1024+tg1024
1318
tokens/s
77.4
tokens/s
789
ms
pp1280+tg3072
1297
tokens/s
64.1
tokens/s
999
ms
pp384+tg1152
1351
tokens/s
85.1
tokens/s
295
ms
pp64+tg1024
1012
tokens/s
91.2
tokens/s
73
ms
pp16+tg1536
371
tokens/s
88.0
tokens/s
54
ms