TEST #2348 RESULTS
01/24/2026 - 10:01 AM
ACCELERATOR
MODEL
119
tokens/s
generation
575
ms
time to first token
2062
tokens/s
prompt
752
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
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2689
tokens/s
134
tokens/s
388
ms
pp4096+tg256
2201
tokens/s
77.7
tokens/s
1.87
sec
pp2048+tg256
2457
tokens/s
107
tokens/s
843
ms
pp2048+tg768
2457
tokens/s
102
tokens/s
843
ms
pp1024+tg1024
2589
tokens/s
121
tokens/s
403
ms
pp1280+tg3072
2495
tokens/s
95.6
tokens/s
521
ms
pp384+tg1152
2291
tokens/s
137
tokens/s
174
ms
pp64+tg1024
1091
tokens/s
151
tokens/s
65
ms
pp16+tg1536
291
tokens/s
143
tokens/s
61
ms