TEST #3588 RESULTS
05/21/2026 - 3:26 PM
ACCELERATOR
MODEL
92.8
tokens/s
generation
678
ms
time to first token
1689
tokens/s
prompt
614
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
64GB
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 19:30:44 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2183
tokens/s
112
tokens/s
478
ms
pp4096+tg256
1925
tokens/s
70.6
tokens/s
2.14
sec
pp2048+tg256
2120
tokens/s
91.4
tokens/s
977
ms
pp2048+tg768
2137
tokens/s
88.7
tokens/s
970
ms
pp1024+tg1024
2090
tokens/s
102
tokens/s
500
ms
pp1280+tg3072
2102
tokens/s
79.1
tokens/s
618
ms
pp384+tg1152
1743
tokens/s
97.8
tokens/s
230
ms
pp64+tg1024
686
tokens/s
102
tokens/s
102
ms
pp16+tg1536
218
tokens/s
91.3
tokens/s
82
ms