TEST #3166 RESULTS
03/23/2026 - 6:42 PM
ACCELERATOR
MODEL
22.1
tokens/s
generation
3.90
sec
time to first token
369
tokens/s
prompt
128
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
8GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:53:31 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
450
tokens/s
25.6
tokens/s
2.30
sec
pp4096+tg256
273
tokens/s
14.6
tokens/s
15.07
sec
pp2048+tg256
421
tokens/s
20.5
tokens/s
4.90
sec
pp2048+tg768
342
tokens/s
18.0
tokens/s
6.04
sec
pp1024+tg1024
478
tokens/s
22.7
tokens/s
2.19
sec
pp1280+tg3072
385
tokens/s
17.6
tokens/s
3.38
sec
pp384+tg1152
486
tokens/s
25.2
tokens/s
820
ms
pp64+tg1024
340
tokens/s
26.9
tokens/s
221
ms
pp16+tg1536
142
tokens/s
27.5
tokens/s
134
ms