TEST #3189 RESULTS
03/25/2026 - 6:41 AM
ACCELERATOR
MODEL
88.7
tokens/s
generation
993
ms
time to first token
1243
tokens/s
prompt
481
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Pro 5P+6E
RAM
18GB
OS
Darwin
Kernel Release
23.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.4.0: Fri Mar 15 00:12:25 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T6030
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1608
tokens/s
98.5
tokens/s
647
ms
pp4096+tg256
1176
tokens/s
63.3
tokens/s
3.50
sec
pp2048+tg256
1452
tokens/s
82.5
tokens/s
1.42
sec
pp2048+tg768
1473
tokens/s
79.8
tokens/s
1.40
sec
pp1024+tg1024
1575
tokens/s
92.0
tokens/s
660
ms
pp1280+tg3072
1499
tokens/s
73.0
tokens/s
864
ms
pp384+tg1152
1538
tokens/s
99.5
tokens/s
259
ms
pp64+tg1024
553
tokens/s
106
tokens/s
125
ms
pp16+tg1536
314
tokens/s
104
tokens/s
59
ms