TEST #1069 RESULTS
06/18/2025 - 12:44 PM
ACCELERATOR
MODEL
88.1
tokens/s
generation
959
ms
time to first token
1344
tokens/s
prompt
498
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
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:29 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6030
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1650
tokens/s
95.1
tokens/s
631
ms
pp4096+tg256
1219
tokens/s
62.9
tokens/s
3.38
sec
pp2048+tg256
1504
tokens/s
82.1
tokens/s
1.37
sec
pp2048+tg768
1459
tokens/s
78.7
tokens/s
1.42
sec
pp1024+tg1024
1590
tokens/s
90.7
tokens/s
654
ms
pp1280+tg3072
1595
tokens/s
74.6
tokens/s
813
ms
pp384+tg1152
1538
tokens/s
99.4
tokens/s
259
ms
pp64+tg1024
1141
tokens/s
107
tokens/s
65
ms
pp16+tg1536
400
tokens/s
103
tokens/s
49
ms