can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI300X (192GB) run GLM-4.5 Air (MoE)?

GLM · MIT · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at Q8_0 · 117.5 GB · 162–242 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.3 GB239–359 tok/sRuns great
Q3_K_M57.2 GB222–332 tok/sRuns great
Q4_K_M73.0 GB202–303 tok/sRuns great
Q5_K_M83.5 GB191–286 tok/sRuns great
Q6_K99.0 GB176–264 tok/sRuns great
Q8_0117.5 GB162–242 tok/sRuns great
FP16221.0 GB110–166 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a AMD Instinct MI300X (192GB)? Add your real numbers →