Quoting Georgi Gerganov
Georgi Gerganov confirms Qwen3.6-27B is a capable local model for daily coding tasks on consumer hardware.
“I can 100% attest to the fact that Qwen3.6-27B is a very capable local model for coding tasks.”
llama.cpp creator Georgi Gerganov endorsed Qwen3.6-27B as a genuinely useful local coding model he runs daily on an M2 Ultra or RTX 5090 with a stripped-down agent harness. It signals that locally-run open models are now practical for real maintainer workflows, though it's an individual anecdote rather than a major industry announcement.