can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3090 (24GB) run Qwen3.6 35B-A3B (MoE)?

Qwen · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3.6 35B-A3B (MoE) at Q3_K_M · 14.9 GB · 197–295 tok/s on a NVIDIA RTX 3090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M14.9 GB197–295 tok/sRuns great
Q4_K_M21.0 GB171–257 tok/sWon't fit
Q5_K_M24.7 GB159–238 tok/sWon't fit
Q6_K28.6 GB147–221 tok/sWon't fit
Q8_036.8 GB128–192 tok/sWon't fit
FP1669.3 GB84–126 tok/sWon't fit
Open the full calculator →Everything a NVIDIA RTX 3090 (24GB) runsQwen3.6 35B-A3B (MoE) on other machinesWhat to buy to run it →

Ran Qwen3.6 35B-A3B (MoE) on a NVIDIA RTX 3090 (24GB)? Add your real numbers →