can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run GLM-4.5 Air (MoE)?

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

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at FP16 · 221.0 GB · 144–217 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.3 GB271–406 tok/sRuns great
Q3_K_M57.2 GB256–384 tok/sRuns great
Q4_K_M73.0 GB238–357 tok/sRuns great
Q5_K_M83.5 GB228–341 tok/sRuns great
Q6_K99.0 GB214–321 tok/sRuns great
Q8_0117.5 GB199–299 tok/sRuns great
FP16221.0 GB144–217 tok/sRuns great

Ran GLM-4.5 Air (MoE) on a AMD Instinct MI355X (288GB)? Add your real numbers →