can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI300X (192GB) run North Mini Code 1.0 (MoE)?

North · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: North Mini Code 1.0 (MoE) at FP16 · 61.0 GB · 229–344 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB323–485 tok/sRuns great
Q3_K_M14.2 GB314–471 tok/sRuns great
Q4_K_M19.2 GB302–453 tok/sRuns great
Q5_K_M23.0 GB294–440 tok/sRuns great
Q6_K25.5 GB288–432 tok/sRuns great
Q8_032.4 GB274–411 tok/sRuns great
FP1661.0 GB229–344 tok/sRuns great

Ran North Mini Code 1.0 (MoE) on a AMD Instinct MI300X (192GB)? Add your real numbers →