← Back to context Comment by iamniels 1 day ago I switched to GLM-5.3 flash on high for this reason. Too many "but wait" in the Deepseek-v4 reasoning. 1 comment iamniels Reply alfiedotwtf 21 hours ago GLM 5.3 Flash was the killer for me. It really feels like we have Claude-approaching models at home.I just wish they kept parameter count down in order to fit entirely within commonly used RAM sizes
alfiedotwtf 21 hours ago GLM 5.3 Flash was the killer for me. It really feels like we have Claude-approaching models at home.I just wish they kept parameter count down in order to fit entirely within commonly used RAM sizes
GLM 5.3 Flash was the killer for me. It really feels like we have Claude-approaching models at home.
I just wish they kept parameter count down in order to fit entirely within commonly used RAM sizes