#qwen3.8

2 stories

#technology #ai efficiency #apple mlx #bonsai 2 27b #customer support #decision models #fine-tune #kev #local deployment #local inference #low-bit models #modal

Kev: Small Decision Models for Self-Training
Train and run Jev-like decision models on your own with Kev.
GitHub · 1m
Bonsai 2 27B: 9x smaller, nearly full power
PrismML's new compressed model runs advanced AI on local devices without meaningful capability loss.
Prismml · 2m