> ## Documentation Index > Fetch the complete documentation index at: https://amd-gaia.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # OEM Bundling > Hardware SKU pre-configuration for AMD OEM partners # OEM Bundling Framework -- Pre-Configuration for Hardware SKUs > **Date:** 2026-04-01 > > **Status:** Planning > > **Target Milestone:** v0.24.0 > > **Priority:** P1 -- drives OEM adoption of GAIA on Ryzen AI devices > > **Related Issues:** > > * [#648](https://github.com/amd/gaia/issues/648) -- OEM bundling framework: pre-configuration for hardware SKUs > * [#649](https://github.com/amd/gaia/issues/649) -- Cost savings telemetry: show users what they save by running locally > * [#644](https://github.com/amd/gaia/issues/644) -- Model Manager UI: download, switch, and update models from the desktop app > * [#615](https://github.com/amd/gaia/issues/615) -- App Store and Distribution Channel Packaging > > **Related Plans:** > > * [desktop-installer](/docs/plans/desktop-installer) -- NSIS desktop installer + bundled Lemonade MSI > * [agent-hub](/docs/plans/agent-hub) -- Agent registry and marketplace > * [Agent UI](/docs/plans/agent-ui) -- Phases A-D overview *** ## 1. Overview AMD's Ryzen AI 400-series is shipping across six major OEM partners: **Acer, ASUS, Dell, HP, GIGABYTE, and Lenovo**. Each partner ships devices with different memory configurations, NPU capabilities, and target audiences. The OEM bundling framework gives these partners a standardized way to pre-configure GAIA so that end users experience zero-touch deployment: plug in the device, and a private AI agent works immediately with no setup required. The first showcase device is the AMD Agent Computer (Halo Box), powered by Ryzen AI MAX+ 395 with 128GB unified memory. *** ## 2. OEM Configuration Manifest Each OEM provides a YAML manifest placed at a well-known path during factory image creation. GAIA checks for this manifest before running its standard first-boot flow. Invalid manifests fall back to the standard `gaia init` flow with a warning. Required fields: `schema_version`, `oem.name`, `hardware.sku`, `models.default`. ```yaml theme={null} # oem-config.yaml -- OEM Bundling Manifest for GAIA schema_version: "1.0" oem: name: "ASUS" display_name: "ASUS AI Suite" support_url: "https://support.asus.com/ai" hardware: sku: "ASUS-ProArt-PX13-HX370" processor: "AMD Ryzen AI 9 HX 370" npu_tops: 50 gpu_compute_units: 12 ram_gb: 32 models: default: "Qwen3.5-35B-A3B-GGUF" preinstalled: - id: "Qwen3-0.6B-GGUF" size_gb: 0.4 purpose: "lightweight-chat" - id: "Qwen3.5-35B-A3B-GGUF" size_gb: 18.0 purpose: "agent-reasoning" - id: "nomic-embed-text-v1.5-GGUF" size_gb: 0.3 purpose: "rag-embedding" skills: bundle: "consumer" # consumer | developer | enterprise | creative enabled: ["chat", "rag", "talk", "summarize"] settings: temperature: 0.7 ctx_size: 32768 first_run: skip_model_download: true skip_hardware_detection: true ``` *** ## 3. Hardware Profiles The framework maps hardware SKUs to model recommendations. OEMs select from predefined profiles or define custom ones in their manifest. | Profile Tier | Representative SKU | NPU TOPS | GPU CUs | RAM | Max Model Size | Recommended Default Model | | ------------- | ---------------------------------- | -------- | ------- | ------ | -------------- | ------------------------- | | **Halo Max+** | Ryzen AI MAX+ 395 (Agent Computer) | 50 | 40 | 128 GB | \~200B (FP4) | Qwen3.5-35B | | **Halo** | Ryzen AI MAX 390 | 50 | 32 | 64 GB | \~70B (FP4) | Qwen3.5-35B | | **High** | Ryzen AI 9 HX 370 | 50 | 12 | 32 GB | \~30B (Q4) | Qwen3.5-35B | | **Mid** | Ryzen AI 7 340 | 39 | 8 | 16 GB | \~7B (Q4) | Qwen3-8B-GGUF | | **Entry** | Ryzen AI 5 320 | 16 | 4 | 16 GB | \~4B (Q4) | Qwen3-4B-Instruct-GGUF | GAIA validates that a model fits the hardware at boot time. If the default model exceeds available memory (RAM minus \~4 GB OS overhead, with 15% model overhead for KV cache), GAIA falls back to the next smaller preinstalled model. *** ## 4. Pre-Installed Model Packages OEMs bundle models onto the factory image or a companion USB drive. Three predefined tiers cover common deployment scenarios. | Tier | Models Included | Total Disk | Target Audience | | ------------ | ------------------------------------------------ | ---------- | -------------------------------- | | **Minimal** | Qwen3-0.6B-GGUF | \~400 MB | Entry-level devices, demo units | | **Standard** | Qwen3-0.6B + Qwen3.5-35B + nomic-embed-text-v1.5 | \~19 GB | Consumer laptops (32+ GB RAM) | | **Full** | Standard + Qwen3-VL-4B + Qwen3-8B | \~25 GB | Developer and Halo-class devices | Pre-installed models are placed at `C:\AMD\GAIA\models\` and symlinked into the user's `~/.gaia/models/` directory on first boot. *** ## 5. OEM Skill Bundles Skill bundles define which GAIA capabilities are enabled out of the box. OEMs pick a predefined bundle (consumer, developer, enterprise, creative) or define a custom list in the manifest. Skills not in the active bundle are hidden from the UI but remain installed -- users can enable additional skills from the Model Manager UI ([#644](https://github.com/amd/gaia/issues/644)) at any time. *** ## 6. Distribution Channels | Channel | Package Format | Auto-Update | Target | | ----------------------- | ----------------------------- | ----------------------- | ---------------------- | | **Windows Store** | MSIX | Via Store | Consumer retail | | **Pre-installed image** | Embedded in OEM Windows image | Via GAIA update channel | Factory install | | **USB provisioning** | ZIP + PowerShell bootstrap | Manual / `gaia update` | IT deployment | | **Enterprise MDM** | MSI + Group Policy template | Via MDM policy | Fleet management | | **winget** | winget manifest | Via winget upgrade | Developer self-install | *** ## 7. Cost Savings Telemetry A key benefit of local AI is cost savings versus cloud APIs. The telemetry module ([#649](https://github.com/amd/gaia/issues/649)) tracks tokens generated and processed locally, then calculates equivalent cloud API costs using published pricing (OpenAI, Anthropic, Google). All data is stored locally in SQLite — nothing leaves the device unless the user explicitly opts into anonymous aggregate reporting. The Agent UI displays a savings summary card showing monthly and lifetime savings. *** ## 8. Phased Rollout * **Phase 1 (v0.24.0):** Ship the Agent Computer (Halo Box) with a production-ready reference OEM config, manifest schema v1.0, bootstrap loader in `gaia init`, cost savings telemetry v1, and Model Manager UI v1. * **Phase 2 (v0.25.0):** Provide OEM partners with a toolkit -- `gaia oem validate` and `gaia oem preview` CLI commands, OEM integration guide, model packaging tools, and an automated test suite for manifest loading. * **Phase 3 (v0.26.0+):** Ship GAIA on all six OEM partner devices through standard distribution channels (Microsoft Store, MDM, winget), with enterprise fleet management tooling and a partner certification program. *** ## 9. GitHub Issue Cross-References | Issue | Title | Relevance | | ---------------------------------------------- | -------------------------------------------- | ------------------------------------------------------- | | [#648](https://github.com/amd/gaia/issues/648) | OEM bundling framework | Primary issue -- this plan is the design document | | [#649](https://github.com/amd/gaia/issues/649) | Cost savings telemetry | Savings calculator and dashboard | | [#644](https://github.com/amd/gaia/issues/644) | Model Manager UI | Hardware-aware model recommendations | | [#615](https://github.com/amd/gaia/issues/615) | App Store and Distribution Channel Packaging | MSIX, winget, Store distribution | | #597 | Setup wizard | First-boot flow that OEM manifest can skip or customize | | #612 | Agent registry | Skill bundles map to registered agents | | #643 | System tray | OEM branding in tray icon and tooltip | | #634 | Always-on agent (heartbeat) | Enterprise fleet health monitoring | | #474 | MCP auto-install | Enterprise MCP server provisioning via manifest |