TEST #812 RESULTS
05/04/2025 - 10:08 AM
ACCELERATOR
MODEL
118
tokens/s
generation
580
ms
time to first token
2128
tokens/s
prompt
756
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:32:50 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2596
tokens/s
132
tokens/s
402
ms
pp4096+tg256
2087
tokens/s
76.6
tokens/s
1.98
sec
pp2048+tg256
2479
tokens/s
106
tokens/s
835
ms
pp2048+tg768
2470
tokens/s
101
tokens/s
838
ms
pp1024+tg1024
2576
tokens/s
120
tokens/s
405
ms
pp1280+tg3072
2558
tokens/s
94.6
tokens/s
508
ms
pp384+tg1152
2481
tokens/s
136
tokens/s
161
ms
pp64+tg1024
1439
tokens/s
150
tokens/s
50
ms
pp16+tg1536
463
tokens/s
142
tokens/s
40
ms