can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4070 (12GB) run Llama 3.1 8B?

Llama · Llama 3.1 Community · estimated for a 12.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.1 8B at Q6_K · 6.6 GB · 46–68 tok/s on a NVIDIA RTX 4070 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K2.6 GB89–134 tok/sRuns great
Q3_K_M3.5 GB74–111 tok/sRuns great
Q4_K_M4.9 GB58–87 tok/sRuns great
Q5_K_M5.7 GB51–77 tok/sRuns great
Q6_K6.6 GB46–68 tok/sRuns great
Q8_08.5 GB37–55 tok/sTight / slow

Ran Llama 3.1 8B on a NVIDIA RTX 4070 (12GB)? Add your real numbers →