can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run Kimi Linear 48B-A3B (MoE)?

Kimi · MIT · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Kimi Linear 48B-A3B (MoE) at FP16 · 98.3 GB · 267–400 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K17.5 GB343–515 tok/sRuns great
Q3_K_M22.7 GB337–506 tok/sRuns great
Q4_K_M30.1 GB329–493 tok/sRuns great
Q5_K_M35.1 GB323–485 tok/sRuns great
Q6_K40.5 GB318–476 tok/sRuns great
Q8_052.3 GB306–459 tok/sRuns great
FP1698.3 GB267–400 tok/sRuns great

Ran Kimi Linear 48B-A3B (MoE) on a AMD Instinct MI355X (288GB)? Add your real numbers →