can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5090 (32GB) run North Mini Code 1.0 (MoE)?

North · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: North Mini Code 1.0 (MoE) at Q5_K_M · 23.0 GB · 211–316 tok/s on a NVIDIA RTX 5090 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB262–393 tok/sRuns great
Q3_K_M14.2 GB244–367 tok/sRuns great
Q4_K_M19.2 GB224–336 tok/sRuns great
Q5_K_M23.0 GB211–316 tok/sRuns great
Q6_K25.5 GB203–304 tok/sTight / slow
Q8_032.4 GB184–275 tok/sWon't fit
FP1661.0 GB132–198 tok/sWon't fit
Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) runsNorth Mini Code 1.0 (MoE) on other machinesWhat to buy to run it →

Ran North Mini Code 1.0 (MoE) on a NVIDIA RTX 5090 (32GB)? Add your real numbers →