can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run GLM-4 9B?

GLM · MIT · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 59–88 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.1 GB194–291 tok/sRuns great
Q3_K_M4.1 GB169–254 tok/sRuns great
Q4_K_M5.7 GB140–210 tok/sRuns great
Q5_K_M6.7 GB126–190 tok/sRuns great
Q6_K7.8 GB115–172 tok/sRuns great
Q8_010.0 GB96–144 tok/sRuns great
FP1618.8 GB59–88 tok/sRuns great

Ran GLM-4 9B on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →