Re:I ran Gemma 4 as a local model in Codex CLI
by shaz0x on Wednesday April 15, 2026 @06:28PM
(#47786170)
On mobile the Q4 vs Q6 tradeoff flips. Gemma 4 E2B at Q4_K_M barely fits in RAM on a 6GB Android, so Q6 isn't on the table. In practice the Q4 hit shows up in tool-call reliability more than general reasoning, which is usually fine for a constrained skill surface.
[ Parent
| on HN ]
There are no comments on this comment yet.