can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5080 (16GB) run North Mini Code 1.0 (MoE)?

North · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: North Mini Code 1.0 (MoE) at Q2_K · 10.5 GB · 210–315 tok/s on a NVIDIA RTX 5080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB210–315 tok/sRuns great
Q3_K_M14.2 GB190–284 tok/sWon't fit
Q4_K_M19.2 GB168–251 tok/sWon't fit
Q5_K_M23.0 GB154–231 tok/sWon't fit
Q6_K25.5 GB146–219 tok/sWon't fit
Q8_032.4 GB128–192 tok/sWon't fit
FP1661.0 GB85–127 tok/sWon't fit

Ran North Mini Code 1.0 (MoE) on a NVIDIA RTX 5080 (16GB)? Add your real numbers →