Meta Open-Sources Muse Glimmer: A 30B Local Agent Model with 3.1x Speed
dl_weekly · x · 2026-08-19
Meta has released Muse Glimmer, a 30-billion-parameter open-source model optimized for local agentic workflows. Quantized to under 20GB, it runs on consumer GPUs and achieves up to 3.1x faster decoding via speculative decoding. It is licensed under Apache 2.0 and supports integrations with llama.cpp and MLX.
Related event: Meta Open-Sources Muse Glimmer, a 30B Local Voice Agent Model(2 posts)→
More from Infra
- Large data centers employ only ~50-150 permanent on-site staff, Microsoft says — brezina · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Oracle down 12% in a week, nearly 50% off June high as OpenAI exposure spooks market — alvelda · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Microsoft Research unveils Magnetar, the fastest zkVM at 10-39x speedups and post-quantum security — jedisct1 · 2026-10-16
- Bonsai 2 2B hits 120 tok/s on iPhone 18 Pro, outpaces Qwen 3.5 2B at half the memory — cephaloform · 2026-10-16