TEST #1394 RESULTS
08/18/2025 - 10:56 PM
ACCELERATOR
MODEL
65.5
tokens/s
generation
1.45
sec
time to first token
886
tokens/s
prompt
342
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
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1046
tokens/s
73.7
tokens/s
992
ms
pp4096+tg256
831
tokens/s
46.3
tokens/s
4.95
sec
pp2048+tg256
970
tokens/s
60.8
tokens/s
2.13
sec
pp2048+tg768
971
tokens/s
57.9
tokens/s
2.13
sec
pp1024+tg1024
979
tokens/s
66.7
tokens/s
1.06
sec
pp1280+tg3072
1026
tokens/s
54.7
tokens/s
1.26
sec
pp384+tg1152
1031
tokens/s
73.8
tokens/s
385
ms
pp64+tg1024
836
tokens/s
78.5
tokens/s
88
ms
pp16+tg1536
284
tokens/s
77.0
tokens/s
68
ms