can-i-run-this-llm

Can I run this LLM?

Can a Laptop CPU, DDR5 dual-channel (16GB) run Llama 3.1 8B?

Llama · Llama 3.1 Community · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Llama 3.1 8B at Q2_K · 2.6 GB · 7–11 tok/s on a Laptop CPU, DDR5 dual-channel (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K2.6 GB7–11 tok/sTight / slow
Q3_K_M3.5 GB6–9 tok/sTight / slow
Q4_K_M4.9 GB4–7 tok/sTight / slow
Q5_K_M5.7 GB4–6 tok/sTight / slow
Q6_K6.6 GB3–5 tok/sTight / slow
Q8_08.5 GB3–4 tok/sTight / slow

Ran Llama 3.1 8B on a Laptop CPU, DDR5 dual-channel (16GB)? Add your real numbers →