Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build
ns123abc · x · 2026-10-16
An open-weights model dubbed Muse-Spark-Open has landed on Hugging Face: an 816B-total / 42B-active MoE whose config reveals low-to-xhigh reasoning effort tiers and multimodal support.
The MLX community quickly shipped a 3-bit quantized build weighing roughly 359 GB, prompting the poster to predict that 512GB M5 Ultra Macs will sell like crazy — it's exactly the class of open model that fits in one high-end Mac for local inference.
Related event: Muse Spark Open Weights Released, Runs on MLX Within 30 Minutes(3 posts)→
More from Infra
- Temporal Serverless Workers on Cloud Run: queue-driven autoscaling, scale to zero — rseroter · 2026-10-16
- LMA brings day-0 model support to TPU for the first time, spanning NVIDIA, AMD, Intel via SGLang — ying11231 · 2026-10-16
- Semtech's analyst-day slide cleanly explains the four signal-integrity impairments — BenBajarin · 2026-10-16
- Fortytwo Engine boosts Qwen3.8-27B accuracy 7% and cuts tokens 25% via Swarm Inference — rohanpaul_ai · 2026-10-16
- Berkeley scholars: concentrated chip supply chain makes a hardwired frontier AI pause feasible — wfithian · 2026-10-16
- Robotics data tokenization landscape: Khala maps peaq, THOR, BitRobot and Axis — 0xSammy · 2026-10-16