TEST #3701 RESULTS
06/08/2026 - 5:45 PM
ACCELERATOR
MODEL
148
tokens/s
generation
363
ms
time to first token
3209
tokens/s
prompt
1093
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
64GB
OS
Darwin
Kernel Release
25.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.5.0: Mon Apr 27 20:39:42 PDT 2026; root:xnu-12377.121.6~2/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4114
tokens/s
151
tokens/s
256
ms
pp4096+tg256
3591
tokens/s
100
tokens/s
1.15
sec
pp2048+tg256
3898
tokens/s
136
tokens/s
533
ms
pp2048+tg768
3871
tokens/s
130
tokens/s
537
ms
pp1024+tg1024
4047
tokens/s
151
tokens/s
259
ms
pp1280+tg3072
4107
tokens/s
123
tokens/s
318
ms
pp384+tg1152
3589
tokens/s
171
tokens/s
112
ms
pp64+tg1024
1284
tokens/s
188
tokens/s
55
ms
pp16+tg1536
379
tokens/s
178
tokens/s
47
ms