TEST #2907 RESULTS
02/26/2026 - 3:16 PM
ACCELERATOR
MODEL
41.4
tokens/s
generation
2.15
sec
time to first token
612
tokens/s
prompt
228
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 20:53:01 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
727
tokens/s
46.5
tokens/s
1.43
sec
pp4096+tg256
534
tokens/s
28.0
tokens/s
7.70
sec
pp2048+tg256
666
tokens/s
37.7
tokens/s
3.10
sec
pp2048+tg768
666
tokens/s
36.1
tokens/s
3.10
sec
pp1024+tg1024
723
tokens/s
42.4
tokens/s
1.44
sec
pp1280+tg3072
716
tokens/s
33.9
tokens/s
1.81
sec
pp384+tg1152
728
tokens/s
47.5
tokens/s
546
ms
pp64+tg1024
547
tokens/s
51.5
tokens/s
133
ms
pp16+tg1536
204
tokens/s
49.2
tokens/s
94
ms