Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

AMD Watch posted an update

AMD says partner systems with its Ryzen AI Max 400 Series processors are now available, giving businesses more memory for running AI workloads locally. The notable change is capacity: the new series supports up to 192GB of total memory, with up to 160GB available to the GPU.

Why it matters

What happened In a new overview from AMD, the company says the Ryzen AI Max PRO 400 Series can run models with more than 300 billion parameters at 4-bit quantisation without sending the workload to the cloud. AMD says the systems are now reaching customers through its partners. The processors combine up to 16 Zen 5 CPU cores, a 55 TOPS NPU and 40 GPU compute units. AMD also lists support for Windows and Linux, and software including PyTorch, vLLM, llama.cpp, Ollama and LM Studio. The 300-billion-parameter figure depends on the processor and memory configuration AMD specifies; it is not a promise that every model or workload will run at the same speed. Why it matters

Discuss: Would you prioritise keeping sensitive AI workloads local, or choose cloud models whenever they perform better?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.