Will it run? / Qwen3 Coder 30B (A3B) / GEEKOM A6 (Ryzen 7 6800H, 32GB)

Can the GEEKOM A6 (Ryzen 7 6800H, 32GB) run Qwen3 Coder 30B (A3B)?

Comfortable Yes, at about 14 tokens/sec (estimated). That reads at a comfortable pace.

14estimated tokens/sec
20.5 GBmemory needed
27.2 GBavailable to the model
76.8 GB/smemory bandwidth
ollama run qwen3-coder:30b-a3b

Check the GEEKOM A6 (Ryzen 7 6800H, 32GB) price →

How we got this number

Each generated token reads the active part of the model from memory once: 1.9 GB. The GEEKOM A6 (Ryzen 7 6800H, 32GB) moves 76.8 GB/s, so the ceiling is 40 tokens/sec. Real machines reach a fraction of that ceiling; we use 60%, an assumption until we get measured runs for this kind of machine. Send us your real numbers and we'll replace the estimate.

Faster machines for Qwen3 Coder 30B (A3B)

Mac Studio M5 Max (40-core GPU, 64GB)120+ tok/s$3,799Check price →
Mac Studio M5 Ultra (96GB)120+ tok/s$5,499Check price →
Mac Studio M5 Ultra (256GB)120+ tok/s$9,499Check price →
Mac mini M5 Pro (64GB)72 tok/sCheck price →

Other models on the GEEKOM A6 (Ryzen 7 6800H, 32GB)

lfm 2.5 8B (A1B)Fast38 tok/s
Qwen 3 30B (A3B)Comfortable14 tok/s
Qwen 3-VL 30B (A3B)Comfortable13 tok/s
Llama 2 7BComfortable12 tok/s
Code Llama 7BComfortable12 tok/s
DeepSeek Coder 6.7BComfortable12 tok/s