High-memory local AI computer
BOSGAME AI PC: A 128 GB local powerhouse
The BOSGAME M5 gives its Radeon 8060S access to most of a 128 GB unified-memory pool. That is the reason to look at it for local AI.
The hardware is the story
Ryzen AI Max+ 395
AMD's high-end Strix Halo processor combines CPU, integrated Radeon graphics, and an NPU in one package.
128 GB LPDDR5X
High-bandwidth unified memory serves the CPU and GPU instead of dividing capacity into separate system-RAM and VRAM pools.
Radeon 8060S
The integrated GPU can access roughly 94–96 GB when the machine's graphics-memory allocation is configured accordingly.
Why unified memory matters for local AI
A conventional desktop may have plenty of system RAM but only 8, 12, or 16 GB on its graphics card. Large models then require quantization, CPU offload, or repeated transfers between memory pools. The M5's shared pool changes that constraint: the GPU can work with far more memory than an ordinary consumer graphics card provides.
Unified memory is slower than the dedicated memory on a high-end graphics card. It wins on capacity. A slower GPU that holds the full workflow can finish jobs that a faster 16 GB card cannot load.
ROCm, PyTorch, and ComfyUI on Windows
AMD now provides ROCm-enabled PyTorch for Ryzen AI Max+ systems on Windows and documents a native ComfyUI setup. No WSL layer is required. Windows still supports less of ROCm than Linux, and AMD lists several setup and workload limits.
What AMD has already demonstrated
AMD ran full-precision FLUX and a roughly 28 GB Wan 2.2 workflow without model offload on Ryzen AI Max+ hardware. FLUX peaked near 34 GB and Wan 2.2 near 42 GB, well beyond the memory on most consumer graphics cards.
What we still need to test
We have not tested a retail M5 yet. A proper review needs sustained performance, thermals, noise, wall power, Windows setup time, reported GPU allocation, and generation times for language, image, and video jobs.