TEST #2913 RESULTS
02/27/2026 - 1:49 AM
ACCELERATOR
MODEL
96.2
tokens/s
generation
990
ms
time to first token
1250
tokens/s
prompt
495
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 4P+6E
RAM
32GB
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 21:09:49 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8142
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1547
tokens/s
107
tokens/s
672
ms
pp4096+tg256
1221
tokens/s
70.3
tokens/s
3.37
sec
pp2048+tg256
1433
tokens/s
89.9
tokens/s
1.44
sec
pp2048+tg768
1417
tokens/s
86.6
tokens/s
1.46
sec
pp1024+tg1024
1504
tokens/s
97.8
tokens/s
690
ms
pp1280+tg3072
1483
tokens/s
82.4
tokens/s
873
ms
pp384+tg1152
1503
tokens/s
107
tokens/s
264
ms
pp64+tg1024
863
tokens/s
115
tokens/s
82
ms
pp16+tg1536
283
tokens/s
110
tokens/s
64
ms