For a long time, local models were basically unusable in Cline. But these models are getting better & smaller 👀 model: lmstudio-community/Qwen3-30B-A3B-GGUF (3-bit, 14.58 GB) hardware: MacBook Pro (M4 Max, 36GB RAM) (run via LM Studio)

Model link:

Note: dial up the context length for best performance in Cline

Can Machine Learning beat the market? Check out this post on my free Substack where I share code and commentary for an XGBoost model and a Random Forest model that both deliver powerful performances.

@lmstudio MLX 8bit quant cooking hard

@lmstudio Real-time speed?

Try Cline today 👇

@lmstudio Devstral also worked well.

@lmstudio This has me elated.

@lmstudio @shubhamtwtss try this.., ig, your damml model

@lmstudio Impressive