Whatever happened to GLM 4.7 Flash hype?

<!-- SC_OFF --><div class="md"><p>Comparing the utility of Qwen3.5-Omni Plus and Flash models for real-time applications. Flash seems very snappy for voice.</p> </div><!-- SC_ON

<!-- SC_OFF --><div class="md"><p>I'm very happy with Z.ai's decision to open source GLM 5.2...</p> <p>With that being said, a successor to GLM-4.7-flash would be AMAZING.

<!-- SC_OFF --><div class="md"><p>I use it to setup other ai hosts with vllm and llama.cpp and it's driving me nuts.</p> <p>It has a completely different approach to things on

<!-- SC_OFF --><div class="md"><p>Im fed up with qwen 3.8 flash next refusing to do certain tasks (e.g. finding vulnerabilites in my code or scanning network related stuff). </p>

<!-- SC_OFF --><div class="md"><p>I'm currently choosing between IQ3_XXS Qwen-3.8-Flash and Q8_0 27B.</p> <p>This month I don't have anything complex enough to justify either's

<!-- SC_OFF --><div class="md"><p>While we are weathering the gemini 3.5 flash hype, keep in mind that according to arena, GLM and Mimo are better.</p> <p><a

<!-- SC_OFF --><div class="md"><p>I wanted to know if theres anything that can improve creative writing for our Local Models? I specificly am asking for qwen models as they are

<!-- SC_OFF --><div class="md"><p><a