AMD's 2026 refresh of Strix Point: the same 12-core Zen 5 / Zen 5c layout and Radeon 890M, with higher clocks, a 55 TOPS NPU and faster LPDDR5X support. A small step over the HX 370, not a new generation.
Recommended for Gaming Local AI & LLMs
| Graphics | AMD Radeon 890M (16 CUs, RDNA 3.5) |
| Memory | 2x DDR5-5600 SODIMM (Up to 128GB) |
| Storage | 3x M.2 2280 PCIe 4.0 (Up to 12TB) |
| Idle Power | 5.5W – 9W |
| Price | $719 barebone · €1,399 (32GB/1TB) |
Gorgon Point Ryzen AI 9 HX 470
| Graphics | AMD Radeon 890M (16 CUs, RDNA 3.5, 3.1 GHz) |
| Memory | 2x DDR5-5600 SODIMM (32GB or 64GB) |
| Storage | 2x M.2 2280 PCIe 4.0 x4 (Up to 8TB) |
| Idle Power | ~8W idle (Robtech, via Starry Hope) |
| Price | $1,399 (32GB/1TB) · $1,699 (64GB/1TB) |
Gorgon Point Ryzen AI 9 HX 470
| Model | AMD Ryzen AI 9 HX 470 (Gorgon Point) |
| Cores / Threads | 12 / 24 (4x Zen 5 + 8x Zen 5c) |
| Boost | Up to 5.2 GHz (Zen 5) / 3.3 GHz (Zen 5c) |
| L3 Cache | 24 MB |
| Default TDP | 28 W (configurable 15–54 W; mini PCs often run 54 W PL1 / 65 W PL2) |
| NPU | AMD XDNA 2, up to 55 TOPS (86 TOPS platform total) |
| Process | TSMC 4 nm |
| iGPU | Radeon 890M, 16 CUs RDNA 3.5, up to 3.1 GHz |
| Media Engine | H.264 / HEVC / AV1 encode and decode |
| Display Output | Up to 4 displays, single display up to 8K |
| Memory Channels | Dual-channel (128-bit) — only when both SODIMM slots are populated |
| Memory Type | DDR5-5600 SODIMM or LPDDR5X (soldered, faster bins than HX 370) |
| Max Memory | Up to 128 GB DDR5 SODIMM |
| Storage | PCIe 4.0 x4 NVMe — 2 to 3 M.2 2280 slots depending on chassis |
| USB4 | Up to 2x 40 Gbps |
| eGPU | OCuLink (PCIe 4.0 x4) on selected models |
| Ethernet | 2.5GbE, dual on premium models |
| Typical Idle | 6 – 10 W at the wall (measured ~7.7 W average in a Minisforum AI X1 Pro-470) |
Local LLM inference, 1080p–1440p gaming with upscaling, software builds and creative workloads in a compact desktop.
| Graphics (iGPU) | Radeon 780M (12 CUs RDNA 3) |
| Memory Architecture | Dual DDR5 5600MHz SODIMM |
| Storage Exp. | 2x PCIe 4.0 NVMe (Raid 0/1 support) |
| Idle Power | 11W – 16W |
| Est. Barebone Cost | $490 - $680 |
Native 1080p AAA gaming, external eGPU docking, Ollama local 7B-13B LLM inference.
| Graphics (iGPU) | Radeon 890M (16 CUs) |
| Memory Architecture | LPDDR5X 7500MT/s (Soldered 32/64GB) |
| Storage Exp. | Dual M.2 PCIe 4.0 x4 |
| Idle Power | 12W – 19W |
| Est. Barebone Cost | $790 - $1,050 |
Ultra-fast local model fine-tuning, 1440p gaming, intensive creative studio workflow.
| Graphics (iGPU) | Radeon 8060S (40 CUs, up to 2.9 GHz) |
| Memory Architecture | LPDDR5X-8000 256-bit, soldered (64GB or 128GB) |
| Storage Exp. | 2x M.2 PCIe 4.0 x4 |
| Idle Power | 10W – 18W |
| Est. Barebone Cost | $1,500 - $2,800 |
Local LLM inference on 30B–120B models, ROCm/AI development, 1440p gaming without a discrete GPU, heavy multi-core builds.