
Use the MoE CPU offload slider in LM Studio to fit a 30B model on your GPU
It started as a toggle and became a layer slider in LM Studio 0.4.0. Where it lives, what it moves, the number to set on an 8, 12 or 16GB card, whether LM Studio runs Qwen3.8 Flash Next, and why Mac MLX models don't have the setting.
Ari Vale · · 8 min






