model
Bonsai 27B: A 27B-Class model that runs on a phone
Running a 27B model on a phone is impressive but has a steep setup, fit for teams with mobile AI needs.
5.5Overall
Utility6
Onboarding4
Craft5
Niche fit7
Longevity5
Five dimensions scored independently; overall is a weighted average. Scores are only comparable within this same rubric.
Good for
Teams building offline, privacy‑focused or low‑latency mobile AI apps
Not for
Teams that only run inference on servers or lack mobile deployment expertise
Project description
prismml.com
Alternatives
Llama 2 7B quantized for mobileMistral 7BTinyLlamaPhi-2