TEST #4114 RESULTS
09/02/2026 - 11:33 AM
ACCELERATOR
MODEL
77.9
tokens/s
generation
1.18
sec
time to first token
1122
tokens/s
prompt
420
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
24GB
OS
Darwin
Kernel Release
25.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.6.0: Fri Jul 31 19:11:03 PDT 2026; root:xnu-12377.161.14~5/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
86.5
tokens/s
779
ms
pp4096+tg256
972
tokens/s
54.5
tokens/s
4.23
sec
pp2048+tg256
1203
tokens/s
72.1
tokens/s
1.72
sec
pp2048+tg768
1210
tokens/s
69.8
tokens/s
1.71
sec
pp1024+tg1024
1327
tokens/s
80.1
tokens/s
783
ms
pp1280+tg3072
1300
tokens/s
66.5
tokens/s
997
ms
pp384+tg1152
1354
tokens/s
87.6
tokens/s
294
ms
pp64+tg1024
1012
tokens/s
93.8
tokens/s
73
ms
pp16+tg1536
382
tokens/s
90.0
tokens/s
52
ms