TEST #3443 RESULTS
05/04/2026 - 6:32 PM
ACCELERATOR
MODEL
99.2
tokens/s
generation
984
ms
time to first token
1265
tokens/s
prompt
503
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
1560
tokens/s
110
tokens/s
666
ms
pp4096+tg256
1229
tokens/s
71.9
tokens/s
3.35
sec
pp2048+tg256
1427
tokens/s
92.6
tokens/s
1.45
sec
pp2048+tg768
1428
tokens/s
89.3
tokens/s
1.45
sec
pp1024+tg1024
1517
tokens/s
101
tokens/s
684
ms
pp1280+tg3072
1500
tokens/s
84.8
tokens/s
863
ms
pp384+tg1152
1458
tokens/s
111
tokens/s
272
ms
pp64+tg1024
972
tokens/s
118
tokens/s
74
ms
pp16+tg1536
298
tokens/s
114
tokens/s
62
ms