You can run local language models on an AMD Ryzen AI Max workstation using Ollama or llama.cpp, but the best setup depends on your operating system and the exact hardware configuration. The clearest starting point is AMD’s Ubuntu 24.04 LTS walkthrough for Ollama; Windows has a separate AMD-documented LM Studio and Vulkan route. Check current compatibility for your specific system before installing: the examples below are version-specific demonstrations, not guarantees for every Ryzen AI Max model.
How do I run an LLM locally on Ryzen AI Max?
Choose a backend that matches your operating system and the GPU support documented for your exact machine. For the most straightforward route, use Ollama on Linux. Choose llama.cpp when you want more direct control over GGUF models, quantization, and GPU offload. On Windows, AMD’s published example uses LM Studio with llama.cpp and Vulkan—not the Linux ROCm setup.
- Before installing: Confirm your Ryzen AI Max model, installed memory, OS version, and the current support information for the ROCm or Vulkan path you intend to use.
- Start small: Load a smaller quantized model first, check where it is running, and then increase model size or context length while monitoring memory use and responsiveness.
- Set realistic expectations: Unified memory expands the range of models you can try, but it does not guarantee that all weights and context fit in GPU-accessible memory or that a large model will respond quickly.
Can I use Ollama on Ryzen AI Max?
Yes. AMD’s May 25, 2026 walkthrough documents Ollama on a Ryzen AI Max+ 395 system with 128GB of unified memory, Ubuntu 24.04 LTS, ROCm 7.2.1, and Ollama 0.20.x. In that setup, the GPU-accessible allocation was configured to 64GB. Treat this as a reproducible example, not a universal recipe: check current ROCm and Ollama compatibility for your exact hardware and software before following it.
Linux: AMD’s Ollama example
- Check the prerequisites. Use the documented Ubuntu 24.04 LTS, ROCm 7.2.1, and Ollama 0.20.x combination as a reference point. Verify current compatibility and the applicable GPU memory configuration for your machine before installing.
- Install Ollama using the installation method appropriate to your system and the current Ollama guidance. Confirm the installed version is compatible with your ROCm environment.
- Download the example model:
ollama pull qwen3.5:35b - Run it:
ollama run qwen3.5:35b - Inspect placement: In another terminal, run
ollama psand check the reported processor placement. AMD’s all-GPU result applies to its 35B demonstration and specified configuration; do not assume a different model or machine will also fit entirely on the GPU.
AMD’s Linux article also reports testing Qwen3.5 9B, 35B-A3B, and 122B-A10B at Q4_K_M quantization. In AMD’s example, the 122B model had a reported 76GB footprint—more than the configured 64GB GPU-accessible allocation—and loaded with mixed placement: 61% GPU and 39% CPU. These are AMD-reported demonstration figures, not independent benchmark results.
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware match#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
When should I use llama.cpp instead?
llama.cpp is a more configurable option for running quantized GGUF models and controlling GPU offload. AMD’s ROCm documentation provides a route for supported Ryzen APUs, with instructions for Linux and Windows. Check the current compatibility material for your exact processor and OS, and install the driver and runtime that apply to that environment.
Check device support before configuring ROCm
Shared memory reporting does not prove ROCm support. AMD’s documentation warns: “The integrated GPU reports a large amount of shared system memory and may not be a supported ROCm device.” Confirm the exact device is supported rather than relying on a memory figure or on the Ryzen AI Max name alone. Follow AMD’s listed Linux package and group prerequisites where applicable.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
Configure and verify offload
In llama.cpp, use model-appropriate settings and confirm which device the runtime selected. AMD documents llama-bench with a GGUF model and -ngl 999 as a benchmark example; that value is not a universal setting for every model or machine. If a model does not fit or performance is poor, reduce GPU offload or context length, or try a smaller quantization.
How is the Windows setup different?
AMD’s Windows example is a distinct path: LM Studio using llama.cpp with Vulkan, AMD Adrenalin 25.8.1, and Variable Graphics Memory (VGM). AMD describes up to 96GB of VGM on a 128GB Ryzen AI Max+ 395 system. That figure is specific to the stated hardware and software context; it does not establish that every Windows ROCm feature is supported or that every Ryzen AI Max system has the same allocation.
Recommended Free Tools
Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
For Llama 4 Scout, AMD reports 109B total parameters and 17B active parameters, while noting that all the model’s weights still need to be held in memory. Its Windows article reports up to 15 tokens per second and a 256,000-token context with Flash Attention enabled and a Q8 KV cache, under the stated example conditions. These are vendor-reported results, not independent measurements or expected speeds for other setups.
How much memory do local models need on Ryzen AI Max?
There is no single memory figure that guarantees a model will fit or feel responsive. The 128GB figure in AMD’s Linux example is total unified system memory, not a promise that every model and context can reside in GPU memory. That Linux setup configured 64GB as GPU-accessible; AMD’s separate Windows article describes up to 96GB of VGM for its specified 128GB system.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
Model weights are only part of the calculation. Quantization changes the weight footprint, while a longer context and its KV cache consume additional memory. GPU allocation and CPU/GPU offload also vary by machine and runtime. Parameter count alone therefore does not establish whether a workload will fit in a particular GPU allocation.
- Begin with a smaller quantized model and a moderate context length.
- Check the runtime’s device-placement report and available memory.
- Increase model size or context gradually, watching for CPU offload, memory pressure, and a response time that is too slow for your use.
- If a model exceeds GPU-accessible memory, determine whether the backend can use mixed CPU/GPU placement and whether the resulting responsiveness is acceptable.
What should I check if performance disappoints?
First verify that your device, operating system, driver, runtime, and model are a supported combination. Then check whether the model is running on the GPU, partly on the CPU, or mostly on the CPU, and whether its context and KV cache are consuming more memory than expected.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Scan for outdated or missing drivers - takes under a minute3Clear out junk files and repair common Windows errorsBest Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
AMD’s ROCm 7.2.1 Ryzen limitations page cautions: “Lower than expected performance may be observed while running some LLM workloads (such as Llama 31B/3B) on AMD Ryzen™ AI MAX+395 processors.” This warning is specific to that ROCm release and does not quantify results for all workloads. Validate your own model and software combination rather than assuming that a large unified-memory configuration guarantees high throughput.
Which Ryzen AI Max workstation should I use?
Check the installed memory configuration, cooling and form factor, operating system, and validated inference backend—not just the processor family name. AMD lists the Framework Desktop, ASUS ROG Flow Z13, HP ZBook Ultra G1a, Corsair AI Workstation 300, and HP Z2 Mini G1a among Ryzen AI Max+ systems available in 128GB configurations. That does not mean every configuration of those product lines has 128GB or identical software support; confirm the exact SKU and compatibility before buying or installing an OS.
AMD’s cited pages are vendor documentation and demonstrations. They establish documented workflows and configuration-specific results, not independent performance rankings across workstations.
Quick Recap
Official documentation
- AMD ROCm Blogs: AI Inference on AMD Ryzen™ AI Max Processor
- AMD: AMD Ryzen™ AI Max+ Upgraded: Run up to 128 Billion parameter LLMs on Windows with LM Studio
- AMD ROCm documentation: llama.cpp inference on ROCm
- AMD ROCm 7.2.1: Ryzen Limitations and recommended settings
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
