TEST #1079 RESULTS
06/19/2025 - 11:13 PM
ACCELERATOR
MODEL
129
tokens/s
generation
554
ms
time to first token
2038
tokens/s
prompt
781
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Max 8P+4E
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 20:24:23 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2719
tokens/s
148
tokens/s
383
ms
pp4096+tg256
2439
tokens/s
94.5
tokens/s
1.69
sec
pp2048+tg256
2589
tokens/s
124
tokens/s
799
ms
pp2048+tg768
2667
tokens/s
119
tokens/s
776
ms
pp1024+tg1024
2462
tokens/s
131
tokens/s
423
ms
pp1280+tg3072
2259
tokens/s
109
tokens/s
574
ms
pp384+tg1152
2171
tokens/s
143
tokens/s
183
ms
pp64+tg1024
800
tokens/s
154
tokens/s
86
ms
pp16+tg1536
231
tokens/s
143
tokens/s
75
ms