Re:Revolut moves to self-hosted GLM
by Tade0 on Tuesday November 03, 2026 @06:29AM
(#50350667)
MoE models can be largely offloaded to system RAM - recent versions of llama.cpp automatically distribute parts of the model, with all the dense parts going into VRAM and just the routed experts residing in system RAM.
I'm currently running Qwen3 Coder Next, which is a 80B A3B model, at 15tps on a 8GB 7700S and 64GB RAM.
It's an idiot (no Thinking), so it has to go over its work several times to get it right, but it's the largest idiot I can feasibly run at the moment.
Also by accident I'm undercutting the only provider of this model on OpenRouter by 40%, doing $0.48/mTok.
Of course at my token rate it would take an entire day to even reach a million tokens, but it's the principle that matters.
I'm currently running Qwen3 Coder Next, which is a 80B A3B model, at 15tps on a 8GB 7700S and 64GB RAM.
It's an idiot (no Thinking), so it has to go over its work several times to get it right, but it's the largest idiot I can feasibly run at the moment.
Also by accident I'm undercutting the only provider of this model on OpenRouter by 40%, doing $0.48/mTok.
Of course at my token rate it would take an entire day to even reach a million tokens, but it's the principle that matters.