can-i-run-this-llm

Can I run this LLM?

Can a AMD RX 9070 XT (16GB) run Gemma 3 27B?

Gemma · Gemma · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Gemma 3 27B at Q2_K · 10.5 GB · 34–51 tok/s on a AMD RX 9070 XT (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB34–51 tok/sTight / slow
Q3_K_M13.4 GB28–42 tok/sWon't fit
Q4_K_M16.6 GB24–36 tok/sWon't fit
Q5_K_M19.3 GB21–32 tok/sWon't fit
Q6_K22.2 GB19–28 tok/sWon't fit
Q8_028.7 GB15–22 tok/sWon't fit
FP1654.0 GB8–12 tok/sWon't fit
Open the full calculator →Everything a AMD RX 9070 XT (16GB) runsGemma 3 27B on other machinesWhat to buy to run it →

Ran Gemma 3 27B on a AMD RX 9070 XT (16GB)? Add your real numbers →