can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run DeepSeek V4 Flash (MoE)?

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

Yes — it runs great.

Best fit: DeepSeek V4 Flash (MoE) at Q3_K_M · 128.1 GB · 269–404 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M128.1 GB269–404 tok/sRuns great

Ran DeepSeek V4 Flash (MoE) on a AMD Instinct MI355X (288GB)? Add your real numbers →