Empero Qwen3.8-35B-A3B

RTX 3060 12GB · Q4_K_M · llama.cpp

Empero’s Qwen3.8-35B-A3B is running on: RTX 3060 12GB 16GB system RAM 262K context ~550 tok/s prefill ~50 tok/s decode

Qwen3.8 distilled into Qwen3.6-35B-A3B. Not official Qwen3.8-27B.

Officialclaimed

@Oluwaphilemon1