can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3090 (24GB) run GLM-4 9B?

GLM · MIT · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at Q8_0 · 10.0 GB · 57–86 tok/s on a NVIDIA RTX 3090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.1 GB135–203 tok/sRuns great
Q3_K_M4.1 GB113–170 tok/sRuns great
Q4_K_M5.7 GB89–134 tok/sRuns great
Q5_K_M6.7 GB79–119 tok/sRuns great
Q6_K7.8 GB70–106 tok/sRuns great
Q8_010.0 GB57–86 tok/sRuns great
FP1618.8 GB33–50 tok/sTight / slow

Ran GLM-4 9B on a NVIDIA RTX 3090 (24GB)? Add your real numbers →