can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run NVIDIA Nemotron 3.5 Bolt 74B A9B?

Nemotron · See model card · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: NVIDIA Nemotron 3.5 Bolt 74B A9B at FP16 · 148.2 GB · 173–260 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K28.8 GB301–452 tok/sRuns great
Q3_K_M39.0 GB283–425 tok/sRuns great
Q4_K_M50.2 GB266–399 tok/sRuns great
Q5_K_M58.9 GB254–381 tok/sRuns great
Q6_K72.4 GB237–356 tok/sRuns great
Q8_078.9 GB230–345 tok/sRuns great
FP16148.2 GB173–260 tok/sRuns great

Ran NVIDIA Nemotron 3.5 Bolt 74B A9B on a AMD Instinct MI355X (288GB)? Add your real numbers →