TEST #546 RESULTS
04/08/2025 - 12:42 AM
ACCELERATOR
MODEL
76.6
tokens/s
generation
1.18
sec
time to first token
1105
tokens/s
prompt
416
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
32GB
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
1332
tokens/s
86.0
tokens/s
780
ms
pp4096+tg256
987
tokens/s
55.6
tokens/s
4.17
sec
pp2048+tg256
1217
tokens/s
71.4
tokens/s
1.70
sec
pp2048+tg768
1211
tokens/s
68.7
tokens/s
1.70
sec
pp1024+tg1024
1323
tokens/s
78.9
tokens/s
785
ms
pp1280+tg3072
1272
tokens/s
65.5
tokens/s
1.02
sec
pp384+tg1152
1340
tokens/s
86.6
tokens/s
297
ms
pp64+tg1024
935
tokens/s
90.2
tokens/s
79
ms
pp16+tg1536
326
tokens/s
86.5
tokens/s
59
ms