TEST #3489 RESULTS
05/10/2026 - 4:50 PM
ACCELERATOR
MODEL
84.4
tokens/s
generation
939
ms
time to first token
1417
tokens/s
prompt
503
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
48GB
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 19:33:25 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1605
tokens/s
97.8
tokens/s
649
ms
pp4096+tg256
1280
tokens/s
61.9
tokens/s
3.22
sec
pp2048+tg256
1470
tokens/s
80.0
tokens/s
1.41
sec
pp2048+tg768
1497
tokens/s
76.1
tokens/s
1.38
sec
pp1024+tg1024
1532
tokens/s
86.4
tokens/s
682
ms
pp1280+tg3072
1583
tokens/s
72.2
tokens/s
821
ms
pp384+tg1152
2112
tokens/s
93.7
tokens/s
189
ms
pp64+tg1024
1257
tokens/s
98.9
tokens/s
58
ms
pp16+tg1536
416
tokens/s
92.8
tokens/s
46
ms