Will it run? / Llama 3 70B / Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB)

Can the Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) run Llama 3 70B?

Won't fit No. Llama 3 70B needs about 41.5 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
41.5 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: 40 GB. The Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) moves 89.6 GB/s, so the ceiling is 2.2 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 70B

Mac Studio M5 Ultra (96GB)25 tok/s$5,499Check price →
Mac Studio M5 Ultra (256GB)25 tok/s$9,499Check price →
Mac Studio M5 Max (40-core GPU, 64GB)12 tok/s$3,799Check price →
Mac mini M5 Pro (64GB)6.1 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