TEST #3516 RESULTS
05/12/2026 - 7:15 AM
ACCELERATOR
MODEL
74.0
tokens/s
generation
1.29
sec
time to first token
1020
tokens/s
prompt
388
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
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:31:09 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1205
tokens/s
82.4
tokens/s
862
ms
pp4096+tg256
905
tokens/s
53.1
tokens/s
4.54
sec
pp2048+tg256
1094
tokens/s
68.7
tokens/s
1.89
sec
pp2048+tg768
1092
tokens/s
66.3
tokens/s
1.89
sec
pp1024+tg1024
1188
tokens/s
75.6
tokens/s
874
ms
pp1280+tg3072
1166
tokens/s
62.8
tokens/s
1.11
sec
pp384+tg1152
1205
tokens/s
82.9
tokens/s
330
ms
pp64+tg1024
972
tokens/s
88.7
tokens/s
77
ms
pp16+tg1536
351
tokens/s
85.4
tokens/s
56
ms