The AMD Ryzen AI MAX+ 395 (codename: "Strix Halo") is the most powerful x86 APU and delivers a significant performance boost

The AMD Ryzen AI MAX+ 395 (codename: "Strix Halo") is the most powerful x86 APU and  delivers a significant performance boost over the competition.

The AMD Ryzen AI MAX+ 395 (codenamed "Strix Halo") is the most powerful x86 APU and delivers a significant performance boost over the competition. Powered by "Zen 5" CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade for the premium thin and light form factor. The Ryzen AI MAX+ 395 is available in options ranging from 32GB all the way up to 128GB of unified memory - out of which up to 96GB can be converted to VRAM through AMD Variable Graphics Memory.

The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required. Deploying new AI text and vision models on Day 1 has never been simpler.

The "Strix Halo" platform extends AMD performance leadership in LM Studio with the new AMD Ryzen AI MAX+ series of processors.

As a primer: the model size is dictated by the number of parameters and the precision used. Generally speaking, doubling the parameter count (on the same architecture) or doubling the precision will also double the size of the model. Most of our competitor's current-generation offerings in this space max out at 32GB on-package memory. This is enough shared graphics memory to run large language models (roughly) up to 16GB in size.

Benchmarking text and vision language models in LM Studio

For this comparison, we will be using the ASUS ROG Flow Z13 with 64GB of unified memory. We will restrict the LLM size to models that fit inside 16GB to ensure that it runs on the competitor's 32GB laptop.

From the results, we can see that the ASUS ROG Flow Z13 - powered by the integrated Radeon 8060S and taking full advantage of the 256 GB/s bandwidth - effortlessly achieves up to 2.2x the performance of the Intel Arc 140V in token throughput.

The performance uplift is very consistent across different model types (whether you are running chain-of-thought DeepSeek R1 Distills or standard models like Microsoft Phi 4) and different parameter sizes.

In time to first token benchmarks, the AMD Ryzen AI MAX+ 395 processor is up to 4x faster than the competitor in smaller models like Llama 3.2 3b Instruct.

Going up to 7 billion and 8 billion models like the DeepSeek R1 Distill Qwen 7b and DeepSeek R1 Distill Llama 8b, the Ryzen AI Max+ 395 is up to 9.1x faster. When looking at 14 billion parameter models (which is approaching the largest size that can comfortably fit on a standard 32GB laptop), the ASUS ROG Flow Z13 is up to 12.2x faster than the Intel Core Ultra 258V powered laptop - more than an order of magnitude faster than the competition!

The larger the LLM, the faster AMD Ryzen AI Max+ 395 processor is in responding to the user query. So whether you are having a conversation with the model or giving it large summarization tasks involving thousands of tokens - the AMD machine will be much faster to respond. This advantage scales with the prompt length - so the heavier the task - the more pronounced the advantage will be.

Text-only LLMs are also slowly getting replaced with highly capable multi-modal models that have vision adapters and visual reasoning capabilities. The IBM Granite Vision is one example and the recently launched Google Gemma 3 family of models is another - with both providing highly capable vision capabilities to next generation AMD AI PCs. Both of these models run incredibly performantly on an AMD Ryzen AI MAX+ 395 processor.

An interesting point to note here: when running vision models, the time to first token metric also effectively becomes the time it takes for the model to analyze the image you give it.

The Ryzen AI Max+ 395 processor is up to 7x faster in IBM Granite Vision 3.2 3b, up to 4.6x faster in Google Gemma 3 4b and up to 6x faster in Google Gemma 3 12b. The ASUS ROG Flow Z13 came with a 64GB memory option so it can also effortlessly run the Google Gemma 3 27B Vision model - which is currently considered the current SOTA (state of