Developer Resource
Accelerate your AI development with curated playbooks and a connected developer community.
Go From Idea to Workflow in Minutes
Start building faster with AMD Ryzen™ AI Halo, from power-on to tokens in minutes, with pre-configured software, regular updates, OS flexibility, and expert support.
- With AMD Ryzen™ AI Max+ PRO 495
- With AMD Ryzen™ AI Max+ 395
Up to
55 TOPS
NPU Performance1
61 FP16 TFLOPS
GPU Performance
16 core / 32 thread
powered by AMD Zen 5 Architecture
192GB
LPDDR5x Unified Memory
Up to
300B
Parameter Models
x86 Architecture
Mature Ecosystem, No Emulation
Available Soon
Up to
50 TOPS
NPU Performance1
60 FP16 TFLOPS
GPU Performance
16 core / 32 thread
powered by AMD Zen 5 Architecture
128GB
LPDDR5x Unified Memory
Up to
200B
Parameter Models
x86 Architecture
Mature Ecosystem, No Emulation
The Ultimate AI Developer Platform
AMD ROCm™ software powers class-leading Generative AI performance and Day 0 support.
AMD Ryzen™ AI Halo vs. Intel Core Ultra X9 388H and Apple M5 Pro2,3
Z Image Turbo INT8
Up to 2.2x faster
Krea 2 Turbo INT8
Up to 2.3x
Ideogram V4 INT8
Up to 1.9x faster
Flux 2 Klien 9b
Up to 1.3x Faster
X 4
FastVideo H3
Up to 2.1x faster
X
LTX 2.5
Up to 3.1x faster
Ace Step XL 1.5 Turbo
Up to 10.8x faster
Stable Music 3
Up to 3.4x faster
Microsoft Trellis 2
Up to 1.3x Faster
X
X = Did Not Run
AMD Ryzen™ AI Max+ PRO 495 processor
Intel Core Ultra X9 388H
Apple M5 Pro
Build, Run, and Deploy Your Way
Real Workflows, Ready to Run
Instant productivity with streamlined onboarding experience, clear guides and ready-to-run apps for image generation, coding assistants, automations, LLMs and more.
Run Bigger AI Locally
Experiment, prototype, and deploy faster – without constraints of cloud costs. With both Linux and Windows support, developers can power their entire journey from experiment to production.
Build AI at Any Stage
From first run to fine-tuning, AMD Ryzen AI Halo supports AI for everyone. Explore hands-on training from beginner to advanced AI workflows and receive prioritized AMD support in GitHub and the AMD AI Developer Program.
AI That Works For You
Unlock real‑time reasoning, persistent memory, and seamless automation across apps and browsers. No token tax.
Pay Once For Cloud Grade Intelligence4
Run sustained AI inference locally with a one-time hardware investment and low estimated monthly electricity cost.
Up to
6x
lower 3-year cost
vs. equivalent cloud API usage in a modeled sustained-use scenario.
Discover how much you could save running AI workloads locally on AMD Client devices.
Enhance the Developer Experience with Software from AMD
AMD Ryzen AI Halo is built for open frameworks and comes pre-installed with the AMD Ryzen AI Halo Developer Center app, a central hub for developers to easily access playbooks, tools and updates.
Image Zoom
Getting started has never been easier. Take advantage of AMD AI Playbooks, guided learning path for developers, including quick and easy setups.
Image Zoom
Coming soon, AMD Sync is a powerful desktop application that lets you seamlessly monitor and manage your AMD Ryzen AI Halo from another device. Access and launch development tools and effortlessly sync files between your machines.
Image Zoom
Discover curated AMD resources, stay aligned with validated software configurations for optimal performance, and seamlessly access and manage pre-installed tools, all from the AMD Ryzen AI Developer Center.
Build What’s Next. Create Without Limits. Play Your Way.
AMD Ryzen™ AI Halo brings powerful performance to a broad ecosystem of x86 apps, software partners, AI models, frameworks, and games. Explore local AI with familiar models and frameworks, bring complex 3D designs to life with creative apps, and tackle demanding video edits with professional tools. From generative AI and creative workflows to immersive gaming, turn your imagination into reality on one compact platform.
![Logo wall from left to right, row 1 [Hell is Us, Unknown 9: Awakening, Wondershare, GitHub Copilot, Blades of Fire, Qwen, The Riftbreaker™, Saints Row, Databiomes, World War Z®: Aftermath, ARKRUNR, Cyberpunk 2077], row 2 [Asterigos: Curse of the Stars, Morphik, Belt, Project Motor Racing, BUFFERZONE, Valor Mortis, llmware, Far Cry® 6, DeepTutor, PUBG Battlegrounds, Blackmagic Design, Open WebUI], row 3 [Voicemod, DIABLO® IV: LORD OF HATRED™, Affinity, Resident Evil™ Village, Moonlighter 2, Superball, CyberLink, McAfee, SOLIDWORKS, Liquid, Dragon’s Dogma 2, The Blood of Dawnwalker], row 4 [Crimson Moon, Monster Hunter Wilds, DEATH STRANDING 2: ON THE BEACH, Crimson Desert, Creatures of Ava, AnythingLLM, Blender, Assassin’s Creed Valhalla, The Invincible, Escape from Duckov, THE LAST OF US™ Part I, Bitdefender], row 5 [Marvel Rivals, AI Producer, The Witcher III Wild Hunt Remastered, Lies of P, Unsloth, LM Studio, OpenAI Codex, The Alters, STYRK AI, God of War™, AVATAR: Frontiers of Pandora™, Horizon Zero Dawn™ Complete Edition for PC], row 6 [Perplexica, UNCHARTED: Legacy of Thieves Collection, FastFlowLM, Resident Evil™ 4, Immortals of Aveum™, PyTorch, Claude, Comfy, Dead Island 2, Perplexity, KeyShot, FlowyAIPC], row 7 [Zoom, Nexa AI, Final Fantasy XVI, Lemonade, Resonance: A Plague Tale Legacy, Continue, Distinct AI, Mafia: The Old Country, World of Tanks HEAT, Starfield, The Thaumaturge, Onimusha: Way of the Sword], row 8 [Starsand Island, Mecha BREAK, Company of Heroes 3, Forspoken, Topaz Labs, Once Human, DeepSeek, Sniper Elite® 5, Iternal, Epic Games, Pluxbox, STAR WARS Jedi: Survivor™], row 9 [Nous, Iterate.ai, Stuntman: Hollywood, DEATHLOOP™, Speechify, Avid, Maxon, A.V. Mapping, llama.cpp, Clive Barker's Hellraiser: Revival, Microsoft, Blink], row 10 [House Flipper 2, Ollama, Call of Duty®: Black Ops 7, Reincubate, The Callisto Protocol, The Elder Scrolls IV: Oblivion Remastered, Warhammer 40,000: Space Marine 2, Frostpunk 2, UDT, Astrion AI, Red Dead Redemption 2, Hugging Face]](/content/dam/amd/en/images/logos/partners/5487300-partner-logos.jpg/jcr:content/renditions/5487300-partner-logos-m.jpg)
Specifications
Name |
Graphics Model |
# of CPU Cores |
# of Threads |
Max. Boost Clock |
CPU Base Clock |
NPU TOPS |
Graphics Core Count |
Default TDP |
FP16 AI Compute |
AMD Ryzen™ AI Halo Developer Platform with Ryzen™ AI Max+ PRO 495 processor |
AMD Radeon™ 8065S Integrated Graphics |
16 |
32 |
Up to 5.2 GHz |
3.1 GHz |
Up to 55 TOPS |
40 |
120W |
Up to 61 TFLOPS |
AMD Ryzen™ AI Halo Developer Platform with Ryzen™ AI Max+ 395 processor |
AMD Radeon™ 8060S Integrated Graphics |
16 |
32 |
Up to 5.1 GHz |
3 GHz |
Up to 50 TOPS |
40 |
120W |
Up to 60 TFLOPS |
Resources
This product is available for purchase and use in the United States. It has been designed and tested to comply with applicable U.S. regulatory requirements.
Footnotes
© 2026 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo, AMD ROCm, Radeon, Ryzen, and combinations thereof are trademarks of Advanced Micro Devices, Inc. Linux® is the registered trademark of Linus Torvalds in the U.S. and other countries. Windows is a registered trademark of Microsoft Corporation in the US and/or other countries. Other product names used in this publication are for identification purposes only and may be trademarks of their respective owners. Certain AMD technologies may require third-party enablement or activation. Supported features may vary by operating system. Please confirm with the system manufacturer for specific features. No technology or product can be completely secure.
- GD-243: Trillions of Operations per Second (TOPS) for an AMD Ryzen processor is the maximum number of operations per second that can be executed in an optimal scenario and may not be typical. TOPS may vary based on several factors, including the specific system configuration, AI model, and software version. GD-243.
- GRHP-25: Testing as of September 2026 by AMD. Average of multiple runs in ComfyUI 0.37. AMD system: AMD Ryzen™ AI Max+ PRO 495 with 192GB memory, VGM set to 128GB, and AMD Software: Adrenalin Edition 26.8.1. Intel comparison system: Intel Panther Lake with Intel Core™ Ultra X9 388H and 64GB memory, Intel® Arc™ B390 and Intel® Arc™ Graphics Driver 32.0.101.8991. Workloads used in the competitive chart: Z Image Turbo, Z Image Turbo INT8, Krea 2 Turbo, Krea 2 Turbo INT8, Ideogram V4, Ideogram V4 INT8, Flux 2 Klien 4b, Flux 2 Klien 9b, Qwen Image 2.1, FastVideo H3, LTX 2.5, Ace Step XL 1.5 Turbo, Stable Music 3, Minimax Music, Yuve, Microsoft Trellis 2, Pixal 3D, and TripoSplat 3D. Performance may vary. GRHP-25.
- GRHP-26: Testing as of September 2026 by AMD. Average of multiple runs in ComfyUI 0.37. AMD system: AMD Ryzen™ AI Max+ PRO 495 with 192GB memory, VGM set to 128GB, and AMD Software: Adrenalin Edition 26.8.1. Apple comparison system: MacBook Pro with Apple M5 Pro, 20-core GPU, 64GB memory, and Metal 4. Where the Apple M5 Pro result was DNR, the chart uses “Runs” and no speedup ratio is calculated. Workloads used: Z Image Turbo, Z Image Turbo INT8, Krea 2 Turbo, Krea 2 Turbo INT8, Ideogram V4, Ideogram V4 INT8, Flux 2 Klien 4b, Flux 2 Klien 9b, Qwen Image 2.1, FastVideo H3, LTX 2.5, Ace Step XL 1.5 Turbo, Stable Music 3, Minimax Music, Yuve, Microsoft Trellis 2, Pixal 3D, and TripoSplat 3D. Performance may vary. GRHP-26.
- SHO-49: Specimen use-case using simplified assumptions. Cloud comparison assumes Claude Sonnet 4.5 standard API pricing of $3/M input tokens and $15/M output tokens, with a 10:1 input-to-output token utilization mix. Local scenario assumes AMD Ryzen™ AI Max+ sustained throughput at 128K context of 36 output tokens/sec and 446 input tokens/sec, measured on pre-production AMD Ryzen™ AI Halo developer platform using LM Studio 0.4.12 and vulkan llama.cpp, AMD Software: Adrenalin Edition™ Drivers 26.10.08. Scenario consumption is modeled at 8 hours/day effective utilization, equivalent to approximately 0.573M output tokens/day and 5.73M input tokens/day, or approximately 6.3M total tokens/day. Electricity assumes 150W sustained “nightmare case” draw at $0.15/kWh for 24 hours/day, or $16.20/month. The $0.15/kWh assumption is a rounded estimate broadly aligned with U.S. Energy Information Administration February 2026 average retail electricity pricing , including 14.36¢/kWh for U.S. total all-sector pricing and 17.65¢/kWh for U.S. total residential pricing Source: https://www.eia.gov/electricity/monthly/current_month/april2026.pdf. Three-year local total includes upfront hardware cost plus 36 months of electricity; cloud total assumes equivalent token consumption over 36 months, pricing for Claude Sonnet 4.5, source: https://platform.claude.com/docs/en/about-claude/pricing. Pricing information fetched as of May 2026. Hardware price is based on AMD Ryzen™ AI Halo Box 128GB, as of 5/10/2026. Actual results may vary with workload, context length, caching, batching, model choice, electricity rate, hardware configuration, utilization, and real-world agent behavior.
Footnotes
© 2026 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo, AMD ROCm, Radeon, Ryzen, and combinations thereof are trademarks of Advanced Micro Devices, Inc. Linux® is the registered trademark of Linus Torvalds in the U.S. and other countries. Windows is a registered trademark of Microsoft Corporation in the US and/or other countries. Other product names used in this publication are for identification purposes only and may be trademarks of their respective owners. Certain AMD technologies may require third-party enablement or activation. Supported features may vary by operating system. Please confirm with the system manufacturer for specific features. No technology or product can be completely secure.
- GD-243: Trillions of Operations per Second (TOPS) for an AMD Ryzen processor is the maximum number of operations per second that can be executed in an optimal scenario and may not be typical. TOPS may vary based on several factors, including the specific system configuration, AI model, and software version. GD-243.
- GRHP-25: Testing as of September 2026 by AMD. Average of multiple runs in ComfyUI 0.37. AMD system: AMD Ryzen™ AI Max+ PRO 495 with 192GB memory, VGM set to 128GB, and AMD Software: Adrenalin Edition 26.8.1. Intel comparison system: Intel Panther Lake with Intel Core™ Ultra X9 388H and 64GB memory, Intel® Arc™ B390 and Intel® Arc™ Graphics Driver 32.0.101.8991. Workloads used in the competitive chart: Z Image Turbo, Z Image Turbo INT8, Krea 2 Turbo, Krea 2 Turbo INT8, Ideogram V4, Ideogram V4 INT8, Flux 2 Klien 4b, Flux 2 Klien 9b, Qwen Image 2.1, FastVideo H3, LTX 2.5, Ace Step XL 1.5 Turbo, Stable Music 3, Minimax Music, Yuve, Microsoft Trellis 2, Pixal 3D, and TripoSplat 3D. Performance may vary. GRHP-25.
- GRHP-26: Testing as of September 2026 by AMD. Average of multiple runs in ComfyUI 0.37. AMD system: AMD Ryzen™ AI Max+ PRO 495 with 192GB memory, VGM set to 128GB, and AMD Software: Adrenalin Edition 26.8.1. Apple comparison system: MacBook Pro with Apple M5 Pro, 20-core GPU, 64GB memory, and Metal 4. Where the Apple M5 Pro result was DNR, the chart uses “Runs” and no speedup ratio is calculated. Workloads used: Z Image Turbo, Z Image Turbo INT8, Krea 2 Turbo, Krea 2 Turbo INT8, Ideogram V4, Ideogram V4 INT8, Flux 2 Klien 4b, Flux 2 Klien 9b, Qwen Image 2.1, FastVideo H3, LTX 2.5, Ace Step XL 1.5 Turbo, Stable Music 3, Minimax Music, Yuve, Microsoft Trellis 2, Pixal 3D, and TripoSplat 3D. Performance may vary. GRHP-26.
- SHO-49: Specimen use-case using simplified assumptions. Cloud comparison assumes Claude Sonnet 4.5 standard API pricing of $3/M input tokens and $15/M output tokens, with a 10:1 input-to-output token utilization mix. Local scenario assumes AMD Ryzen™ AI Max+ sustained throughput at 128K context of 36 output tokens/sec and 446 input tokens/sec, measured on pre-production AMD Ryzen™ AI Halo developer platform using LM Studio 0.4.12 and vulkan llama.cpp, AMD Software: Adrenalin Edition™ Drivers 26.10.08. Scenario consumption is modeled at 8 hours/day effective utilization, equivalent to approximately 0.573M output tokens/day and 5.73M input tokens/day, or approximately 6.3M total tokens/day. Electricity assumes 150W sustained “nightmare case” draw at $0.15/kWh for 24 hours/day, or $16.20/month. The $0.15/kWh assumption is a rounded estimate broadly aligned with U.S. Energy Information Administration February 2026 average retail electricity pricing , including 14.36¢/kWh for U.S. total all-sector pricing and 17.65¢/kWh for U.S. total residential pricing Source: https://www.eia.gov/electricity/monthly/current_month/april2026.pdf. Three-year local total includes upfront hardware cost plus 36 months of electricity; cloud total assumes equivalent token consumption over 36 months, pricing for Claude Sonnet 4.5, source: https://platform.claude.com/docs/en/about-claude/pricing. Pricing information fetched as of May 2026. Hardware price is based on AMD Ryzen™ AI Halo Box 128GB, as of 5/10/2026. Actual results may vary with workload, context length, caching, batching, model choice, electricity rate, hardware configuration, utilization, and real-world agent behavior.