AMD Ryzen AI Max+ 395 Local AI Workstation, 64GB — 48GB VRAM | Alden Tech
Local AI, Low Power
$2,799
Built around AMD's Ryzen AI Max+ 395 platform: a combined CPU, GPU, and NPU sharing 64GB of high-speed unified memory, with up to 48GB configurable as dedicated GPU memory (VGM) for local model inference — no separate graphics card needed. Because this is unified memory, the GPU can also draw on additional shared memory beyond that 48GB figure depending on workload and backend, so it isn't a hard ceiling. Practical target: roughly 20B–35B-class models, depending on quantization and context length. The Radeon 8060S integrated GPU runs on AMD's ROCm 7 platform, backed by an NPU rated up to 50 TOPS (126 TOPS combined system-wide) for AI-accelerated workloads. Configured with your choice of Ubuntu Desktop 24.04 or Windows 11 Pro — Linux has the broader ROCm-based serving ecosystem on this platform, but Windows is a fully viable path too; the real difference is tool-specific, not a blanket OS ranking. Ships with LM Studio installed and configured by default — the same Vulkan/llama.cpp backend on either OS. Ollama and standalone llama.cpp are available through the AI Tooling Package for more advanced setups: Ollama runs on Vulkan on Windows (its Linux ROCm support doesn't extend to Windows) or natively via ROCm 7 on Ubuntu; llama.cpp supports either Vulkan or ROCm/HIP on both operating systems.
AI Profile
- Total VRAM: 48GB
- GPU: 1x AMD Radeon 8060S Graphics
Workload Categories
- Local LLM inference
- Private company AI assistant
- RAG / document search
- AI-assisted development
- Local image generation
- AI experimentation
- Multi-user internal AI
- Sensitive-data workflows
Specifications
| cpu | AMD Ryzen™ AI Max+ 395 |
|---|---|
| gpu | AMD Radeon 8060S Graphics |
| AI Engine Performance | AMD Ryzen™ AI NPU Computing Power: Up to 50 TOPS | Total Computing Power: Up to 126 TOPS |
| memoryCapacity | 64GB LPDDR5x-8000MT/s |
| storage | 2TB PCIe 4.0 |
| cooling | Copper Base, 6 Heat Pipes Dual Fans & Phase-Change Cooling 160W Peak, 130W Sustained |
| networking | 2× 10GbE LAN (RJ45) - Wi-Fi 7 | Bluetooth® 5.4 |
| operatingSystem | Ubuntu Desktop 24.04 or Windows 11 Pro |
| powerSupply | AC INPUT (100-240V ~6A 50-60Hz, Internal DC 12V/26.6A, 320W MAX) |
| LLM Software & Tooling | LM Studio included by default (same Vulkan/llama.cpp backend on Windows or Ubuntu). Ollama and llama.cpp also available via the AI Tooling Package — support is tool-specific, not an OS-blanket rule: Ollama is Vulkan-only on Windows (its Linux ROCm support doesn't extend to Windows) and runs natively via ROCm on Ubuntu; llama.cpp supports either Vulkan or ROCm/HIP on both operating systems. |
| Practical Model Range | ~20B–35B-class models (quantization/context dependent) |
| System Access | Full SSH and root/administrator access — same as any PC we sell. Nothing is locked down or requires our involvement. |
Available Options
- Preinstalled AI Tooling Package (+$250) — Ollama and llama.cpp (alternative inference backends), Open WebUI, and RAG document ingestion pipeline — installed and configured before pickup.
There is no online checkout for this system yet — mention any option you want when you contact us.
Warranty
3-Year Parts & Labor Warranty — see the full policy.
LLM Benchmark Results
These are published third-party benchmark results for the AMD Ryzen AI Max+ 395 platform this system is built on — not tests performed by Alden Tech, and not independently reproduced by us. Results below used different operating systems, backends (ROCm vs. Vulkan), model files, quantizations, prompt lengths, and context settings, so they are not directly comparable to each other. A configured context limit is not the same as a demonstrated occupied prompt length — see each result's notes. Sources are linked on each result.
| Model | Prompt tok/s | Generation tok/s | Backend | OS | Notes |
|---|---|---|---|---|---|
| GPT-OSS 20B | 401.46 | 44.58 | Ollama | Windows 11 Pro 24H2 | GPU result on Windows 11 Pro 24H2. Source reports RAM 64GB and VRAM 64GB; these describe unified memory, not an extra dedicated pool. Quantization, GPU backend, prompt length and test date unreported. Single interactive task, not a concurrency validation. [B64-01] Source |
| GPT-OSS 120B | 209.07 | 33.87 | Ollama | Windows 11 Pro 24H2 | Same 64GB EVO-X2 GPU test. MoE active compute is different from total parameters; do not generalize this fit/speed to arbitrary 120B models or long contexts. Quantization and backend unreported; single interactive task. [B64-02] Source |
See the full Business Hardware lineup: Business Hardware.
Sold by Alden Tech — veteran-owned custom PC builder in Spartanburg, South Carolina. Call or text (864) 381-8201. Contact