Will it run? / Qwen2.5-VL 7B / Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB)

Can the Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) run Qwen2.5-VL 7B?

Usable, but slow Yes, at about 9.0 tokens/sec (estimated). It works, but you'll wait on longer answers.

9.0estimated tokens/sec
7.5 GBmemory needed
27.2 GBavailable to the model
89.6 GB/smemory bandwidth
ollama run qwen2.5vl:7b

Check the Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) price →

How we got this number

Each generated token reads the whole model from memory once: 6 GB. The Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) moves 89.6 GB/s, so the ceiling is 15 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 Qwen2.5-VL 7B

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)82 tok/s$3,799Check price →
Mac mini M5 Pro (24GB)41 tok/s$1,699Check price →

Other models on the Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB)

lfm 2.5 8B (A1B)Fast44 tok/s
Llama 3.2 1BFast41 tok/s
Qwen 3 1.7BFast38 tok/s
Granite 3.1 moe 1BFast38 tok/s
minicpm v4.6 1BFast34 tok/s
Gemma 2 2BFast34 tok/s