TEST #3444 RESULTS
05/04/2026 - 7:06 PM
ACCELERATOR
MODEL
101
tokens/s
generation
980
ms
time to first token
1272
tokens/s
prompt
508
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 4P+6E
RAM
16GB
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 19:33:43 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T8142
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1567
tokens/s
112
tokens/s
662
ms
pp4096+tg256
1232
tokens/s
72.2
tokens/s
3.34
sec
pp2048+tg256
1434
tokens/s
93.8
tokens/s
1.44
sec
pp2048+tg768
1433
tokens/s
90.3
tokens/s
1.44
sec
pp1024+tg1024
1520
tokens/s
103
tokens/s
683
ms
pp1280+tg3072
1517
tokens/s
85.7
tokens/s
853
ms
pp384+tg1152
1501
tokens/s
113
tokens/s
264
ms
pp64+tg1024
933
tokens/s
121
tokens/s
76
ms
pp16+tg1536
308
tokens/s
116
tokens/s
60
ms