Apu Memory Tuner

Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the CPU. Use when the user mentions Ryzen AI, Strix Halo / Strix Point / Krackan / Phoenix / Hawk Point, Ryzen AI Max, gfx1150 / gfx1151 / gfx1152, integrated Radeon, iGPU memory, UMA Frame Buffer Size, AMD Variable Graphics Memory, VGM, GTT, GART, TTM, pages_limit, amd-ttm, amd-debug-tools, "shared GPU memory", "dedicated GPU memory", carve-out, "not enough VRAM", "out of VRAM", "GPU OOM", llama.cpp on

500 stars 47 forksProductivity & Notes Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add amd/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add amd/skills --skill apu-memory-tuner
Manual install
git clone --depth 1 https://github.com/amd/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/staging/apu-memory-tuner ~/.claude/skills/apu-memory-tuner

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# APU Memory Tuner

Help the user inspect and tune the shared-vs-dedicated memory split on AMD
Ryzen APUs with unified memory architecture (UMA). The user states intent
("I want to run a 70B model", "I just want my games to be smooth"); this
skill picks the numbers, explains the trade-offs, and applies the change
where it can.

## What's actually going on

On a UMA APU (Strix Halo, Strix Point, Krackan, Phoenix, Hawk Point, etc.)
the CPU and integrated Radeon share **one physical pool of DRAM**. There is
no separate VRAM chip. Two logical knobs cut that pool up:

| Knob | Where set | What it does | Reversible? |
|---|---|---|---|
| **Dedicated VRAM** (a.k.a. UMA Frame Buffer / carve-out / GART) | BIOS, requires reboot | Permanently reserves DRAM for the GPU. CPU can't see it. | Only via BIOS. |
| **Shared GPU memory** (a.k.a. GTT) | Kernel/driver-managed | Dynamic, OS-reclaimable cap on how much system RAM the GPU may map at a time. | Yes; Linux: `amd-ttm`. Windows: no user knob. |

Key insight the rest of this skill rests on: **"VRAM" and shared RAM run at
the same speed on UMA**, because they're the same DRAM. So the right default
for AI workloads is small VRAM + large GTT, not the other way around.

## When to use

Use this skill when the user wants to:

- Run a model that doesn't fit ("out of VRAM", "GPU OOM" on an iGPU).
- Inspect the current memory split before changing anything.
- Move the slider toward more shared memory (LLMs, large image gen) or
Read the full skill on GitHub

Details

Skill name
apu-memory-tuner
Repository
amd/skills
Path
staging/apu-memory-tuner/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Apu Memory Tuner skill do?

Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the CPU. Use when the user mentions Ryzen AI, Strix Halo / Strix Point / Krackan / Phoenix / Hawk Point, Ryzen AI Max, gfx1150 / gfx1151 / gfx1152, integrated Radeon, iGPU memory, UMA Frame Buffer Size, AMD Variable Graphics Memory, VGM, GTT, GART, TTM, pages_limit, amd-ttm, amd-debug-tools, "shared GPU memory", "dedicated GPU memory", carve-out, "not enough VRAM", "out of VRAM", "GPU OOM", llama.cpp on

How do I install the Apu Memory Tuner skill?

Claude Code plugin: /plugin marketplace add amd/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Apu Memory Tuner popular?

It lives in amd/skills, which has 500 GitHub stars and 47 forks.

Related skills

Eaiapps Guided Install

500

amd/skills

Guides a user through installing the AI Workbench (AIWB) onto a Kubernetes cluster end-to-end — preflight cluster readiness (access, StorageClass, GPU operator, required operators/CRDs), install the Helm charts in the correct order, and verify the deployment is healthy with plain-language failure triage. Use when a user wants to install, deploy, or stand up AIWB / the AI Workbench / the enterprise AI stack on a K8s cluster, or asks why their install failed partway. Use PROACTIVELY when a user is following helm/INSTALL.md by hand. Do NOT activate for onboarding models to AIM, general kubectl/he

DevOps & Cloud47

Flydsl Kernel Authoring

500

amd/skills

Comprehensive reference for authoring FlyDSL GPU kernels on AMD GPUs. Covers the layout algebra, tiled copy/MMA, buffer ops, loop-carried range loops, SharedAllocator (LDS), autotuning, and common patterns. Use when writing, reviewing, or understanding FlyDSL kernel code.

Writing & Content47

Flydsl Kernel Trace Analysis

500

amd/skills

Profile GPU kernels using rocprofv3 to collect ATT instruction-level traces, then analyze the trace data using hotspot_analyzer.py to identify top-K stall hotspots (VMEM-load, VMEM-wait, LDS/SMEM-wait, barrier, MFMA stalls) mapped back to source lines, and produce an actionable optimization plan. Also analyzes rocprofv3 PMC counter CSVs (L2 hit rate, partial reads, over-fetch). Usage: /kernel-trace-analysis <cmd> Can also analyze an existing dispatch dir directly: /kernel-trace-analysis --dir <path>

Data & Analytics47

Moat Cuda to Rocm

500

amd/skills

Port a CUDA project to ROCm/HIP for AMD GPUs. Strategy selection, the AMD-strict-where-CUDA-is-lenient fault classes, wavefront-size portability, library substitutions, and the validation bar. Use when planning, implementing, reviewing or validating a CUDA-to-HIP port, or when a HIP build compiles but misbehaves at runtime.

Productivity & Notes47

Project Architect

259

ersinkoc/project-architect

Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts. Generates 4 interconnected docs — SPECIFICATION.md, IMPLEMENTATION.md, TASKS.md, BRANDING.md — plus a self-contained PROMPT.md for autonomous execution by any coding agent. Includes interactive tech stack selection, design pattern recommendations, and architecture decisions with trade-off analysis. Trigger when user wants to: plan a project, create specs, architect a system, break work into tasks, choose a tech stack, get design pattern advice, generate a coding agent prompt

Productivity & Notes31

Personal Assistant

473

ailabs-393/ai-labs-claude-skills

This skill should be used whenever users request personal assistance tasks such as schedule management, task tracking, reminder setting, habit monitoring, productivity advice, time management, or any query requiring personalized responses based on user preferences and context. On first use, collects comprehensive user information including schedule, working habits, preferences, goals, and routines. Maintains an intelligent database that automatically organizes and prioritizes information, keeping relevant data and discarding outdated context.

Productivity & Notes117

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.