TEST #2669 RESULTS
02/15/2026 - 5:44 PM
ACCELERATOR
MODEL
119
tokens/s
generation
567
ms
time to first token
2197
tokens/s
prompt
772
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
2649
tokens/s
139
tokens/s
394
ms
pp4096+tg256
2152
tokens/s
77.4
tokens/s
1.92
sec
pp2048+tg256
2475
tokens/s
106
tokens/s
837
ms
pp2048+tg768
2507
tokens/s
102
tokens/s
826
ms
pp1024+tg1024
2639
tokens/s
121
tokens/s
396
ms
pp1280+tg3072
2620
tokens/s
95.6
tokens/s
496
ms
pp384+tg1152
2633
tokens/s
137
tokens/s
153
ms
pp64+tg1024
1565
tokens/s
150
tokens/s
47
ms
pp16+tg1536
536
tokens/s
142
tokens/s
36
ms