Can I run it?
Can I run Qwen3 Coder 30B A3B Instruct on GeForce RTX 4090?
Tight fit
Tight fit fully on your GeForce RTX 4090 at UD-Q5_K_XL, 8K context, about 188–257 tok/s. Weights 20.2 GB plus 0.75 GB of KV cache — 21.5 GB of 22.3 GB usable.
Best quantUD-Q5_K_XL
Working context8K
Max that fits8K
Speed188–257 tok/s
Weights20.2 GB
KV cache0.75 GB
Total21.5 GB
Usable22.3 GB
Qwen3 Coder 30B A3B Instruct details · GeForce RTX 4090 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:UD-Q5_K_XL -c 8192 -ngl 48
Ollama
ollama run qwen3
LM Studio
lms get unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF # Then load quant UD-Q5_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-Q5_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 4090? — Tight fit, Q4_K_M, 137–187 tok/s
- Can I run Qwen3 Coder Next on GeForce RTX 4090? — Tight fit, UD-IQ1_M, 124–169 tok/s
- Can I run Qwen2.5 Coder 32B Instruct on GeForce RTX 4090? — Tight fit, Q4_K_M, 25–34 tok/s
Updated 2026-10-17. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.