TEST #1115 RESULTS
06/25/2025 - 2:40 PM
ACCELERATOR
MODEL
126
tokens/s
generation
555
ms
time to first token
2043
tokens/s
prompt
774
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
2586
tokens/s
140
tokens/s
403
ms
pp4096+tg256
2392
tokens/s
87.7
tokens/s
1.72
sec
pp2048+tg256
2614
tokens/s
116
tokens/s
792
ms
pp2048+tg768
2591
tokens/s
111
tokens/s
799
ms
pp1024+tg1024
2626
tokens/s
128
tokens/s
397
ms
pp1280+tg3072
2578
tokens/s
105
tokens/s
504
ms
pp384+tg1152
2230
tokens/s
143
tokens/s
178
ms
pp64+tg1024
538
tokens/s
154
tokens/s
125
ms
pp16+tg1536
230
tokens/s
147
tokens/s
75
ms