can-i-run-this-llm

Can I run this LLM?

Can a Laptop CPU, DDR5 dual-channel (16GB) run GPT-OSS 20B (MoE)?

GPT-OSS · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: GPT-OSS 20B (MoE) at Q2_K · 11.5 GB · 10–15 tok/s on a Laptop CPU, DDR5 dual-channel (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.5 GB10–15 tok/sTight / slow
Q3_K_M11.5 GB10–15 tok/sTight / slow
Q4_K_M11.6 GB10–15 tok/sTight / slow
Q5_K_M11.7 GB10–15 tok/sTight / slow
Q6_K12.0 GB10–14 tok/sWon't fit
Q8_012.1 GB9–14 tok/sWon't fit
FP1613.8 GB9–13 tok/sWon't fit
Open the full calculator →Everything a Laptop CPU, DDR5 dual-channel (16GB) runsGPT-OSS 20B (MoE) on other machinesWhat to buy to run it →

Ran GPT-OSS 20B (MoE) on a Laptop CPU, DDR5 dual-channel (16GB)? Add your real numbers →