can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA A100 (80GB) run Llama 3.1 8B?

Llama · Llama 3.1 Community · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.1 8B at Q8_0 · 8.5 GB · 114–171 tok/s on a NVIDIA A100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K2.6 GB208–312 tok/sRuns great
Q3_K_M3.5 GB186–279 tok/sRuns great
Q4_K_M4.9 GB158–238 tok/sRuns great
Q5_K_M5.7 GB145–218 tok/sRuns great
Q6_K6.6 GB134–200 tok/sRuns great
Q8_08.5 GB114–171 tok/sRuns great

Ran Llama 3.1 8B on a NVIDIA A100 (80GB)? Add your real numbers →