The underlying Qwen 3.8 Max model is huge
2.4 trillion total parameters. But only around 95 billion are activated for an individual task. That mixture-of-experts approach lets it pull in the relevant parts of the model instead of activating everything.
Perplexity Portable Computer runs the whole AI agent on your own machine.
Not a chatbot. The full agent that browses, runs tools, reads your files, and finishes tasks. All of it, local. The model, the orchestrator, the tools, the file access. Your data doesn't leave your
The surprising part is not the 27B model - it is the hardware claim
Qwen 3.8 27B reportedly running locally on an 8GB RTX 4060 via Unsloth IQ4_XS, with 64k context, 14.6GB on disk, ~150 tok/s prefill, and ~5 tok/s decode with native MTP.
Qwen 3.8-27B reads your coaching calls and writes the notes for you.
Alibaba dropped it on August 14th, and Token Harbor just added a free route to run it. No GPU. No 55GB download. You paste a prompt and go. → 1 million tokens of context, so feed it your whole document
You have reached the end of the archive
All of qwen38