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 · 117.4 GB · 162–243 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K35.9 GB255–382 tok/sRuns great
Q3_K_M47.6 GB235–353 tok/sRuns great
Q4_K_M67.0 GB209–313 tok/sRuns great
Q5_K_M78.7 GB196–293 tok/sRuns great
Q6_K91.1 GB183–275 tok/sRuns great
Q8_0117.4 GB162–243 tok/sRuns great
FP16220.9 GB110–166 tok/sWon't fit

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