?>
john_alan

Gemma 3 on M4 Max

john_alan

Choosing the right model?

john_alan

Time out of https interface

noseph47

No HTTPS

Odd-Environment-7193

DeepSeek V3 is the shit.

john_alan

Ollama heavy quantisation

john_alan

Apple adds PQ primitives to iMessage

menschmaschine5

[MOD] The Daily Question Thread

john_alan

Upgrading as my Baratza seems broke

john_alan

Swift Arrays for large datamodels

john_alan

Are any of the 4070ti cards LHR?