can-i-run-this-llm

Can I run this LLM?

Can a AMD RX 9070 XT (16GB) run DeepSeek-R1-Distill 14B?

DeepSeek · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: DeepSeek-R1-Distill 14B at Q5_K_M · 10.5 GB · 38–57 tok/s on a AMD RX 9070 XT (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB60–91 tok/sRuns great
Q3_K_M7.3 GB50–76 tok/sRuns great
Q4_K_M9.0 GB43–64 tok/sRuns great
Q5_K_M10.5 GB38–57 tok/sRuns great
Q6_K12.1 GB33–50 tok/sTight / slow
Q8_015.7 GB27–40 tok/sWon't fit
FP1629.6 GB15–23 tok/sWon't fit

Ran DeepSeek-R1-Distill 14B on a AMD RX 9070 XT (16GB)? Add your real numbers →