Qwen 35B-A3B MoE vs 27B dense in local coding tests: ~4× faster, much smaller quality gap than I expected
英文标题：Qwen 35B-A3B MoE vs 27B dense in local coding tests: ~4× faster, much smaller quality gap than I expected
I compared Qwen 35B-A3B MoE against Qwen 27B dense on a series of local coding-maintenance tasks. On my R9700/llama.cpp setup, the MoE model generated about 3.9× faster (~116 vs ~30 tok/s), but the coding-quality difference was much smaller than I expected. Both usually handled ordinary bug fixes an
打开原文相关 2 · 机会 0
中文
I compared Qwen 35B-A3B MoE against Qwen 27B dense on a series of local coding-maintenance tasks. On my R9700/llama.cpp setup, the MoE model generated about 3.9× faster (~116 vs ~30 tok/s), but the coding-quality difference was much smaller than I expected. Both usually handled ordinary bug fixes an
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
I compared Qwen 35B-A3B MoE against Qwen 27B dense on a series of local coding-maintenance tasks. On my R9700/llama.cpp setup, the MoE model generated about 3.9× faster (~116 vs ~30 tok/s), but the coding-quality difference was much smaller than I expected. Both usually handled ordinary bug fixes an