can-i-run-this-llm

Can I run this LLM?

Can a AMD RX 9070 XT (16GB) run Qwen3.6 35B-A3B (MoE)?

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

Yes, but it's tight.

Best fit: Qwen3.6 35B-A3B (MoE) at Q2_K · 12.3 GB · 195–292 tok/s on a AMD RX 9070 XT (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB195–292 tok/sTight / slow
Q3_K_M16.6 GB169–254 tok/sWon't fit
Q4_K_M22.1 GB145–217 tok/sWon't fit
Q5_K_M26.5 GB130–195 tok/sWon't fit
Q6_K29.3 GB122–182 tok/sWon't fit
Q8_036.9 GB104–156 tok/sWon't fit
FP1669.4 GB65–97 tok/sWon't fit
Open the full calculator →Everything a AMD RX 9070 XT (16GB) runsQwen3.6 35B-A3B (MoE) on other machinesWhat to buy to run it →

Ran Qwen3.6 35B-A3B (MoE) on a AMD RX 9070 XT (16GB)? Add your real numbers →