Re:Kimi K2.7 Code is generally available in GitHub Copilot
by pbgcp2026 on Saturday July 04, 2026 @03:26AM
(#48783355)
I personally found in my work (long non-programming business-related context, 150k+) that only Gemma 4 31B full precision and full context works reasonably well. MoE Gemma 4, even non–quantised, makes clear logical mistakes or omissions. On real tasks. If I compare them on tiny tests – yes, sure, even i2 quants work great! :-)
[ Parent
| on HN ]
There are no comments on this comment yet.