can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA L40S (48GB) run Llama 3.2 1B?

Llama · Llama 3.2 Community · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.2 1B at FP16 · 2.5 GB · 147–220 tok/s on a NVIDIA L40S (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.8 GB243–365 tok/sRuns great
Q5_K_M0.9 GB231–347 tok/sRuns great
Q6_K1.0 GB220–330 tok/sRuns great
Q8_01.3 GB200–300 tok/sRuns great
FP162.5 GB147–220 tok/sRuns great

Ran Llama 3.2 1B on a NVIDIA L40S (48GB)? Add your real numbers →