This guy has the Qwen 3.8 177b MoE running on 12gb vram with 64gb of ram, getting 24.4 tokens/sec. A bit more resource hungry than the Qwen3.6 35b, but not by much and still well within the realm of home usage for what is essentially a Frontier model.
does frontier mean like, cutting edge? and isn’t that a moving target
Yes and yes