BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

llama.cpp Improves RDNA3.5 MoE Performance

Sep 16, 2026, first seen via Training & inference tooling releases

llama.cpp release b10997 broadened its RDNA3.5 MoE tile heuristic and improved pooled performance by 11.1% on a tested Radeon 8060S.

Read the original at github.comOpens the publisher's site in a new tab

More in Open-weight & owned stack