can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run DeepSeek-R1-Distill 14B?

DeepSeek · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: DeepSeek-R1-Distill 14B at Q6_K · 12.1 GB · 12–19 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB23–34 tok/sRuns great
Q3_K_M7.3 GB19–28 tok/sRuns great
Q4_K_M9.0 GB16–24 tok/sRuns great
Q5_K_M10.5 GB14–21 tok/sRuns great
Q6_K12.1 GB12–19 tok/sRuns great
Q8_015.7 GB10–15 tok/sTight / slow
FP1629.6 GB6–8 tok/sTight / slow

Ran DeepSeek-R1-Distill 14B on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →