TEST #1794 RESULTS
11/13/2025 - 9:38 PM
ACCELERATOR
MODEL
72.5
tokens/s
generation
1.13
sec
time to first token
1061
tokens/s
prompt
409
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
16GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Wed Sep 17 21:41:45 PDT 2025; root:xnu-12377.1.9~141/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1295
tokens/s
82.0
tokens/s
803
ms
pp4096+tg256
1127
tokens/s
48.0
tokens/s
3.66
sec
pp2048+tg256
1249
tokens/s
65.5
tokens/s
1.65
sec
pp2048+tg768
1248
tokens/s
62.5
tokens/s
1.66
sec
pp1024+tg1024
1273
tokens/s
73.3
tokens/s
816
ms
pp1280+tg3072
1271
tokens/s
58.9
tokens/s
1.02
sec
pp384+tg1152
1190
tokens/s
83.7
tokens/s
333
ms
pp64+tg1024
685
tokens/s
91.4
tokens/s
103
ms
pp16+tg1536
214
tokens/s
86.9
tokens/s
84
ms