can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run GLM-4 9B?

GLM · MIT · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 168–253 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB291–437 tok/sRuns great
Q3_K_M5.0 GB278–417 tok/sRuns great
Q4_K_M6.2 GB263–395 tok/sRuns great
Q5_K_M7.1 GB253–380 tok/sRuns great
Q6_K8.3 GB241–361 tok/sRuns great
Q8_010.0 GB225–337 tok/sRuns great
FP1618.8 GB168–253 tok/sRuns great

Ran GLM-4 9B on a AMD Instinct MI355X (288GB)? Add your real numbers →