GPU Setup¶
Configure AMD integrated graphics for AI workloads on the MS-S1 MAX.
Overview¶
The AMD Ryzen AI Max+ 395 (Strix Halo) APU combines CPU and GPU on a single chip with access to system memory. Unlike discrete GPUs with dedicated VRAM, the integrated RDNA 3.5 graphics shares the 128GB LPDDR5X-8000 quad-channel system memory.
For a comprehensive explanation of the APU architecture, memory subsystem, and design trade-offs, see Hardware Architecture.
Quick Reference¶
| Aspect | MS-S1 MAX APU |
|---|---|
| Architecture | RDNA 3.5 |
| Compute Units | 40 CUs |
| GPU ID | gfx1151 |
| Memory | Shared 128GB LPDDR5X-8000 (quad-channel, soldered) |
| Bandwidth | ~256 GB/s peak, ~210-220 GB/s real-world |
| ROCm Support | Native (Ubuntu 26.04 ships ROCm 7.1 in Universe; gfx1151 supported upstream) |
Why APU for LLMs?¶
The MS-S1 MAX's 128GB configuration enables running large models that exceed typical discrete GPU VRAM:
- 70B models at high quantization - Full Q6 or Q8 fits in memory
- 405B models at lower quantization - Q2-Q3 within reach
- No model offloading - Entire model stays in accessible memory
- Simple setup - No PCIe passthrough needed
The tradeoff is lower memory bandwidth compared to discrete GPUs, resulting in slower tokens/second. However, the ability to run larger models often outweighs raw speed.
Section Contents¶
Quick Start¶
Get from bare Ubuntu 26.04 LTS to running LLMs on GPU in one page:
- Linux 7.0 (default),
apt install rocm, VRAM allocation, Ollama
ROCm Installation¶
Native ROCm installation for Ubuntu 26.04:
- APU compatibility and current support status
- In-distro ROCm 7.1 vs upstream AMD repo (newer ROCm)
- Verification with rocminfo and rocm-smi
Driver Updates¶
Keeping AMD drivers current:
- Checking installed versions
- Update procedures
- Handling conflicts
- Rollback if needed
Memory Configuration¶
Optimizing memory for AI workloads:
- Software VRAM allocation with amd-ttm (108-115GB)
- UMA Frame Buffer Size settings
- Kernel parameter alternatives
- Bandwidth considerations
Related Documentation¶
- BIOS Setup - Configure BIOS for optimal APU performance
- Hardware - MS-S1 MAX specifications
- GPU Containers - ROCm in Docker
- Unified Memory - Memory concepts (Apple Silicon focused, but concepts apply)