TEST #3582 RESULTS
05/21/2026 - 2:57 AM
ACCELERATOR
MODEL
162
tokens/s
generation
375
ms
time to first token
3197
tokens/s
prompt
1114
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
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 20:41:15 PDT 2026; root:xnu-12377.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4003
tokens/s
184
tokens/s
261
ms
pp4096+tg256
3340
tokens/s
115
tokens/s
1.23
sec
pp2048+tg256
3775
tokens/s
153
tokens/s
549
ms
pp2048+tg768
3784
tokens/s
147
tokens/s
548
ms
pp1024+tg1024
3891
tokens/s
168
tokens/s
269
ms
pp1280+tg3072
3879
tokens/s
136
tokens/s
336
ms
pp384+tg1152
3646
tokens/s
179
tokens/s
110
ms
pp64+tg1024
1909
tokens/s
193
tokens/s
38
ms
pp16+tg1536
550
tokens/s
185
tokens/s
34
ms