can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4080 (16GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at Q2_K · 9.7 GB · 185–278 tok/s on a NVIDIA RTX 4080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K9.7 GB185–278 tok/sRuns great
Q3_K_M12.9 GB166–250 tok/sTight / slow
Q4_K_M18.2 GB143–214 tok/sWon't fit
Q5_K_M21.3 GB132–197 tok/sWon't fit
Q6_K24.7 GB121–182 tok/sWon't fit
Q8_031.8 GB104–157 tok/sWon't fit
FP1659.9 GB67–101 tok/sWon't fit

Ran GLM-4.7 Flash (MoE) on a NVIDIA RTX 4080 (16GB)? Add your real numbers →