TEST #1745 RESULTS
11/07/2025 - 2:45 PM
ACCELERATOR
MODEL
106
tokens/s
generation
697
ms
time to first token
1644
tokens/s
prompt
629
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
64GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:17:51 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2095
tokens/s
123
tokens/s
497
ms
pp4096+tg256
1921
tokens/s
74.4
tokens/s
2.15
sec
pp2048+tg256
2061
tokens/s
100
tokens/s
1.00
sec
pp2048+tg768
2022
tokens/s
85.9
tokens/s
1.02
sec
pp1024+tg1024
2082
tokens/s
111
tokens/s
500
ms
pp1280+tg3072
1794
tokens/s
84.7
tokens/s
722
ms
pp384+tg1152
1783
tokens/s
123
tokens/s
223
ms
pp64+tg1024
808
tokens/s
132
tokens/s
86
ms
pp16+tg1536
231
tokens/s
118
tokens/s
76
ms