Lean-QwenFlash runs Alibaba's 125B Qwen3.8-Flash-Next at 20 tok/s on just 8GB RAM and 16GB VRAM by streaming MoE experts from ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible resultsSome results have been hidden because they may be inaccessible to you
Show inaccessible results