TEST #898 RESULTS
05/18/2025 - 7:03 PM
ACCELERATOR
MODEL
124
tokens/s
generation
557
ms
time to first token
2011
tokens/s
prompt
766
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
32GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:49 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2709
tokens/s
139
tokens/s
385
ms
pp4096+tg256
2428
tokens/s
87.6
tokens/s
1.70
sec
pp2048+tg256
2611
tokens/s
114
tokens/s
793
ms
pp2048+tg768
2571
tokens/s
110
tokens/s
805
ms
pp1024+tg1024
2371
tokens/s
127
tokens/s
439
ms
pp1280+tg3072
2606
tokens/s
104
tokens/s
499
ms
pp384+tg1152
1911
tokens/s
141
tokens/s
207
ms
pp64+tg1024
700
tokens/s
152
tokens/s
97
ms
pp16+tg1536
193
tokens/s
145
tokens/s
89
ms