TEST #1075 RESULTS
06/19/2025 - 8:43 AM
ACCELERATOR
MODEL
39.7
tokens/s
generation
2.19
sec
time to first token
606
tokens/s
prompt
222
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
8GB
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 19:48:46 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
713
tokens/s
45.8
tokens/s
1.46
sec
pp4096+tg256
520
tokens/s
27.1
tokens/s
7.91
sec
pp2048+tg256
660
tokens/s
36.6
tokens/s
3.13
sec
pp2048+tg768
659
tokens/s
35.5
tokens/s
3.14
sec
pp1024+tg1024
720
tokens/s
41.3
tokens/s
1.44
sec
pp1280+tg3072
712
tokens/s
33.1
tokens/s
1.82
sec
pp384+tg1152
720
tokens/s
46.1
tokens/s
552
ms
pp64+tg1024
542
tokens/s
46.5
tokens/s
137
ms
pp16+tg1536
210
tokens/s
45.0
tokens/s
92
ms