can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run GLM-5.2 (MoE)?

GLM · MIT · estimated for a 288.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: GLM-5.2 (MoE) at Q2_K · 253.9 GB · 197–295 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K253.9 GB197–295 tok/sTight / slow
Q3_K_M342.7 GB170–255 tok/sWon't fit
Q4_K_M465.8 GB143–215 tok/sWon't fit
Q5_K_M560.8 GB128–191 tok/sWon't fit
Q6_K625.9 GB119–178 tok/sWon't fit
Q8_0801.4 GB100–150 tok/sWon't fit
FP161508.0 GB61–92 tok/sWon't fit
Open the full calculator →Everything a AMD Instinct MI355X (288GB) runsGLM-5.2 (MoE) on other machinesWhat to buy to run it →

Ran GLM-5.2 (MoE) on a AMD Instinct MI355X (288GB)? Add your real numbers →