can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run GLM-4.5 Air (MoE)?

GLM · MIT · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at Q5_K_M · 78.7 GB · 17–25 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K35.9 GB30–45 tok/sRuns great
Q3_K_M47.6 GB25–37 tok/sRuns great
Q4_K_M67.0 GB19–29 tok/sRuns great
Q5_K_M78.7 GB17–25 tok/sRuns great
Q6_K91.1 GB15–22 tok/sWon't fit
Q8_0117.4 GB12–18 tok/sWon't fit
FP16220.9 GB7–10 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →