TEST #1789 RESULTS
11/13/2025 - 5:58 AM
ACCELERATOR
MODEL
77.1
tokens/s
generation
1.18
sec
time to first token
1111
tokens/s
prompt
417
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
32GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1335
tokens/s
85.2
tokens/s
779
ms
pp4096+tg256
979
tokens/s
55.6
tokens/s
4.20
sec
pp2048+tg256
1209
tokens/s
71.2
tokens/s
1.71
sec
pp2048+tg768
1206
tokens/s
69.2
tokens/s
1.71
sec
pp1024+tg1024
1324
tokens/s
79.0
tokens/s
785
ms
pp1280+tg3072
1298
tokens/s
65.3
tokens/s
998
ms
pp384+tg1152
1369
tokens/s
86.6
tokens/s
291
ms
pp64+tg1024
951
tokens/s
92.8
tokens/s
78
ms
pp16+tg1536
324
tokens/s
89.5
tokens/s
59
ms