# Nvidia offers Muse Spark Open weights and NIM deployment container

_Published Thursday, October 15, 2026 at 2:22 PM EDT · AI, Infrastructure · Latest · Tier 2 — Notable_

![Nvidia offers Muse Spark Open weights and NIM deployment container — Primary](https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/open-model-unbox.webp)

Nvidia says developers can download Meta's Muse Spark Open in NVFP4 format from Hugging Face and deploy it through a downloadable Nvidia NIM container. The container automatically selects a serving backend and numerical precision for the detected hardware.

The model has 816B total parameters, activates 42B per token and supports a 1M-token context window. Nvidia says the NVFP4 checkpoints reduce its memory footprint on Blackwell Ultra hardware. Developers can also fine-tune the model through NeMo AutoModel using Hugging Face checkpoints without conversion. Nvidia claims higher throughput and lower cost per token, but supplies no numerical comparison.

## Sources

- [NVIDIA Technical Blog](https://developer.nvidia.com/blog/scale-agentic-coding-workflows-with-metas-muse-spark-open-on-nvidia-gb300-nvl72/)

---
Canonical: https://techandbusiness.org/newswire/5TAmDyeK6zOWyrAl0O2hUc
Published: 2026-10-15T18:22:32.172Z
Story chronology: 2026-10-15T18:00:01.000Z
Retrieved: 2026-10-15T21:02:11.335Z
Publisher: Tech & Business (techandbusiness.org)