TEST #2262 RESULTS
01/12/2026 - 8:41 PM
ACCELERATOR
MODEL
41.2
tokens/s
generation
2.18
sec
time to first token
608
tokens/s
prompt
226
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
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:32:47 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
720
tokens/s
46.9
tokens/s
1.44
sec
pp4096+tg256
526
tokens/s
27.5
tokens/s
7.83
sec
pp2048+tg256
655
tokens/s
37.6
tokens/s
3.15
sec
pp2048+tg768
656
tokens/s
36.0
tokens/s
3.15
sec
pp1024+tg1024
716
tokens/s
42.3
tokens/s
1.45
sec
pp1280+tg3072
708
tokens/s
33.3
tokens/s
1.83
sec
pp384+tg1152
726
tokens/s
46.6
tokens/s
548
ms
pp64+tg1024
560
tokens/s
51.5
tokens/s
132
ms
pp16+tg1536
200
tokens/s
49.1
tokens/s
97
ms