Will it run? / gpt-oss 20B / GEEKOM A6 (Ryzen 7 6800H, 32GB)

Can the GEEKOM A6 (Ryzen 7 6800H, 32GB) run gpt-oss 20B?

Comfortable Yes, at about 11 tokens/sec (estimated). That reads at a comfortable pace.

11estimated tokens/sec
15.5 GBmemory needed
27.2 GBavailable to the model
76.8 GB/smemory bandwidth
ollama run gpt-oss:20b

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: 2.4 GB. The GEEKOM A6 (Ryzen 7 6800H, 32GB) moves 76.8 GB/s, so the ceiling is 32 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 gpt-oss 20B

Mac Studio M5 Ultra (96GB)120+ tok/s$5,499Check price →
Mac Studio M5 Ultra (256GB)120+ tok/s$9,499Check price →
Mac Studio M5 Max (40-core GPU, 64GB)119 tok/s$3,799Check price →
Mac mini M5 Pro (24GB)60 tok/s$1,699Check price →

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

lfm 2.5 8B (A1B)Fast38 tok/s
Qwen2.5-VL 3BComfortable14 tok/s
Gemma 3 4BComfortable14 tok/s
Qwen 3-VL 4BComfortable14 tok/s
translateGemma 4BComfortable14 tok/s
Qwen3.5 4BComfortable14 tok/s