Can a Ryzen AI Max+ 395 128GB run Qwen3 32B?

In practice

Memory is not the problem here, bandwidth is. Qwen3 32B at Q8_0 fits with 61.14 GB to spare, and the Ryzen AI Max+ 395 128GB reads memory at 256 GB/s. Every token needs about 34.8 GB read out of it, which puts the ceiling near 4.3 tokens per second. That is slower than reading: a 500-token answer takes about 2 minutes.

It is fine for jobs you start and walk away from, and tiring for conversation. A smaller file raises the speed in proportion: Q6_K would run at about 5.5 tokens per second, at some cost in quality. A smaller model, or a mixture-of-experts model that reads only a fraction of its weights per token, is the other way out, and both are listed further down.

Reading a 4,000-token prompt, roughly a long email or a few pages of text, takes about 20 seconds before the first word appears. That part is limited by compute and not by bandwidth, so it follows a different spec from the writing speed.

The numbers

Qwen3 32B has 32.76 billion parameters across 64 layers. The Ryzen AI Max+ 395 128GB has 128 GB of unified memory at 256 GB/s, of which about 96 GB is left for a model once the operating system has taken its share.

9 of the 9 levels fit entirely. Levels marked degraded are listed for completeness, not as advice.

How long a conversation it holds

Memory rises with the length of the conversation because the attention cache keeps a key and a value for every token. At Q8_0, the longest window that still fits on this device is 32k tokens. Setting the window to what you need and no more is the cheapest way to buy back memory.

The settings we would use

llama-server -m <model>.gguf -ngl all -c 8192 -fa on

In Ollama, set OLLAMA_CONTEXT_LENGTH to the window you want, run ollama ps while the model is loaded and check that the processor column reads 100% GPU. If it shows a split on a model that fits, the Ollama guide shows how to fix it. The llama.cpp flags guide explains each option above.

What else a Ryzen AI Max+ 395 128GB runs well

For comparison, these are the other popular models that fit this device at a sound quantization, best pairings first.

The same model on nearby hardware

Memory decides whether Qwen3 32B loads and bandwidth decides how quickly it answers. Here is what a step down, a card with the same memory and a step up do with it.

Wait for the first word2.8 s

Then writes at4.3 tok/s

Whole answer43 s

YouWhy does my model use more memory when the conversation gets longer?

Model

Simulated from our estimate at a 512-token question, not a recording. Assumes nothing else is competing for the GPU.

Questions people ask

Keep going

Everything the Ryzen AI Max+ 395 128GB runs, the full breakdown for Qwen3 32B, how the numbers are made in the methodology, or a different pairing in the calculator.