Will it run? / Llama 3.3 70B / Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB)

Can the Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) run Llama 3.3 70B?

Won't fit No. Llama 3.3 70B needs about 44.5 GB of memory, and the Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) can give a model about 27.2 GB. You'd need a machine with more memory, or a smaller model.

–estimated tokens/sec
44.5 GBmemory needed
27.2 GBavailable to the model
89.6 GB/smemory bandwidth

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: 43 GB. The Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) moves 89.6 GB/s, so the ceiling is 2.1 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 Llama 3.3 70B

Mac Studio M5 Ultra (96GB)23 tok/s$5,499Check price →
Mac Studio M5 Ultra (256GB)23 tok/s$9,499Check price →
Mac Studio M5 Max (40-core GPU, 64GB)11 tok/s$3,799Check price →
Mac mini M5 Pro (64GB)5.7 tok/sCheck price →

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

Qwen 3 30B (A3B)Comfortable16 tok/s
Qwen3 Coder 30B (A3B)Comfortable16 tok/s
Qwen 3-VL 30B (A3B)Comfortable15 tok/s
Qwen3.5 35B (A3B)Comfortable14 tok/s
Qwen3.6 35B (A3B)Comfortable14 tok/s
gpt-oss 20BComfortable13 tok/s