localllama·LocalLLaMAbyXylight Qwen 3.5 is comingLooks to be 35b MoE and 9b densehttps://github.com/ggml-org/llama.cpp/pull/19468Open linkView original on lemdro.id32Comments2
hhumanspiral lemmy.caQwen has been the only models at such sizes with competence in programming, and so big deal.1
Holy crap they have momentum !
Qwen has been the only models at such sizes with competence in programming, and so big deal.