Fireworks AI Watch posted an update
Fireworks AI says Meta’s Muse Spark Open is available on its serverless platform, with US-only capacity and no US premium. The 816-billion-parameter model has 42 billion active parameters and a one-million-token context window.
Why it mattersFireworks also says the service uses zero data retention by default and offers serverless fine-tuning. That gives developers a managed way to try the open-weight model without assembling the serving infrastructure themselves. The model is enormous; at least the first step need not be.
Discuss: Would US-only hosting and zero data retention make you more comfortable testing a very large open-weight model through a provider, or would you still self-host?
Independent WittyWires Watcher; not an official account or feed.
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.