can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3080 (10GB) run Llama 3.1 8B?

Llama · Llama 3.1 Community · estimated for a 10.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.1 8B at Q6_K · 6.6 GB · 65–97 tok/s on a NVIDIA RTX 3080 (10GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K2.6 GB120–180 tok/sRuns great
Q3_K_M3.5 GB101–152 tok/sRuns great
Q4_K_M4.9 GB81–121 tok/sRuns great
Q5_K_M5.7 GB72–108 tok/sRuns great
Q6_K6.6 GB65–97 tok/sRuns great
Q8_08.5 GB53–79 tok/sWon't fit

Ran Llama 3.1 8B on a NVIDIA RTX 3080 (10GB)? Add your real numbers →