TEST #2668 RESULTS
02/15/2026 - 5:42 PM
ACCELERATOR
MODEL
124
tokens/s
generation
578
ms
time to first token
1940
tokens/s
prompt
747
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
32GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:29 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2662
tokens/s
138
tokens/s
392
ms
pp4096+tg256
2364
tokens/s
87.2
tokens/s
1.74
sec
pp2048+tg256
2407
tokens/s
115
tokens/s
859
ms
pp2048+tg768
2499
tokens/s
110
tokens/s
828
ms
pp1024+tg1024
2289
tokens/s
127
tokens/s
455
ms
pp1280+tg3072
2605
tokens/s
104
tokens/s
499
ms
pp384+tg1152
1813
tokens/s
141
tokens/s
218
ms
pp64+tg1024
646
tokens/s
152
tokens/s
105
ms
pp16+tg1536
171
tokens/s
145
tokens/s
99
ms