TEST #2667 RESULTS
02/15/2026 - 5:41 PM
ACCELERATOR
MODEL
119
tokens/s
generation
564
ms
time to first token
2211
tokens/s
prompt
775
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
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 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2678
tokens/s
133
tokens/s
390
ms
pp4096+tg256
2177
tokens/s
79.1
tokens/s
1.89
sec
pp2048+tg256
2481
tokens/s
106
tokens/s
835
ms
pp2048+tg768
2504
tokens/s
102
tokens/s
827
ms
pp1024+tg1024
2636
tokens/s
121
tokens/s
396
ms
pp1280+tg3072
2584
tokens/s
95.4
tokens/s
504
ms
pp384+tg1152
2606
tokens/s
140
tokens/s
154
ms
pp64+tg1024
1687
tokens/s
150
tokens/s
44
ms
pp16+tg1536
548
tokens/s
143
tokens/s
36
ms