Can I run it?

Can I run Qwen3 Coder 30B A3B Instruct on GeForce RTX 5090?

Tight fit

Tight fit fully on your GeForce RTX 5090 at UD-Q6_K_XL, 8K context, about 290–396 tok/s. Weights 24.5 GB plus 0.75 GB of KV cache — 25.8 GB of 29.9 GB usable. Up to 32K context still fits.

Qwen3 Coder 30B A3B Instruct details · GeForce RTX 5090 page · How this estimate is made

Run commands

llama-server -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:UD-Q6_K_XL -c 8192 -ngl 48

ollama run qwen3

lms get unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
# Then load quant UD-Q6_K_XL

Assumptions

• Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
• KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
• UD-Q6_K_XL size is the real GGUF file size from Hugging Face.
• 0.5 GB is reserved because this GPU also drives a display, then 5% of the rest is left free.
• Speed is quoted at 8K context, not at the maximum context that still fits.

Larger models that also fit

• Can I run Kwaipilot KAT Coder V2.5 Dev on GeForce RTX 5090? — Runs, Q5_K_M, 210–286 tok/s
• Can I run Qwen3 Coder Next on GeForce RTX 5090? — Tight fit, UD-IQ3_S, 169–230 tok/s
• Can I run Qwen2.5 Coder 32B Instruct on GeForce RTX 5090? — Runs, Q5_K_M, 39–53 tok/s

Updated 2026-10-17. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.