can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4090 (24GB) run GLM-4.7 Flash (MoE)?

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

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at Q3_K_M · 14.6 GB · 190–285 tok/s on a NVIDIA RTX 4090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.3 GB208–312 tok/sRuns great
Q3_K_M14.6 GB190–285 tok/sRuns great
Q4_K_M18.3 GB174–261 tok/sTight / slow
Q5_K_M21.4 GB162–243 tok/sWon't fit
Q6_K24.7 GB151–227 tok/sWon't fit
Q8_031.8 GB132–198 tok/sWon't fit
FP1659.9 GB88–132 tok/sWon't fit

Ran GLM-4.7 Flash (MoE) on a NVIDIA RTX 4090 (24GB)? Add your real numbers →