# Meta’s Muse Glimmer is available on Fireworks AI

> The 30-billion-parameter model is offered on Fireworks’ serverless and on-demand services, with design features aimed at long-running agents.

Oossa · 2026-10-23 · https://oossa.com/en/meta-s-muse-glimmer-is-available-on-fireworks-ai

Meta’s Muse Glimmer, a 30-billion-parameter model built for multi-step agent tasks, is available on Fireworks AI through serverless and on-demand deployments. It supports text and image input and a context window of more than 128,000 tokens.

Fireworks says its small key-value cache helps reduce the cost of serving long agent sessions at scale. Meta-reported benchmark results include 74.6 on DeepSearch QA and 51.2 on SWE-Bench Pro; the post says those results used high reasoning effort. The model’s knowledge cutoff is January 4, 2026, so current information must come from tools.

## The facts

- Muse Glimmer is released under the Apache 2.0 license.
- Fireworks offers serverless and on-demand deployments; the source gives no launch date.

## Why it matters

Teams building long-running agents can try Muse Glimmer on Fireworks without arranging GPU capacity themselves, though the source does not give pricing or independent benchmark results.

## Sources & references

1. [Muse Glimmer from Meta on Fireworks: Ideal for your always-on agents](https://fireworks.ai/blog/meta-muse-glimmer-30b/) – Fireworks AI

Last updated: 2026-10-23