TEST #853 RESULTS
05/11/2025 - 3:23 AM
ACCELERATOR
MODEL
74.5
tokens/s
generation
1.21
sec
time to first token
1064
tokens/s
prompt
403
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
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:22:58 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1314
tokens/s
79.9
tokens/s
792
ms
pp4096+tg256
957
tokens/s
53.9
tokens/s
4.30
sec
pp2048+tg256
1159
tokens/s
67.0
tokens/s
1.78
sec
pp2048+tg768
1185
tokens/s
66.3
tokens/s
1.74
sec
pp1024+tg1024
1313
tokens/s
74.1
tokens/s
793
ms
pp1280+tg3072
1220
tokens/s
63.3
tokens/s
1.06
sec
pp384+tg1152
1347
tokens/s
86.1
tokens/s
297
ms
pp64+tg1024
809
tokens/s
90.5
tokens/s
89
ms
pp16+tg1536
270
tokens/s
89.3
tokens/s
69
ms