# Unsloth adds local support for NVIDIA Nemotron 3.5 and Meta Muse Spark Open

> The open‑source Unsloth app now runs NVIDIA’s Nemotron 3.5 models and Meta’s Muse Spark Open on a PC, with memory requirements listed for each.

Oossa · 2026-10-15 · https://oossa.com/en/unsloth-adds-local-support-for-nvidia-nemotron-3-5-and-meta-muse-spark-open

Unsloth released version 0.1.908‑beta on 2026‑10‑15, adding the ability to run NVIDIA’s Nemotron 3.5 models and Meta’s Muse Spark Open locally. The Bolt variant of Nemotron 3.5 fits on a 24 GB GPU, while the larger Super VL version needs about 64 GB at 1‑bit precision. Meta’s Muse Spark Open runs on a 256 GB GPU at 2‑bit. The update also improves prompt caching for coding agents and adds support for text‑diffusion training.

## The facts

- Nemotron 3.5 Bolt runs on 24 GB of GPU memory
- Muse Spark Open uses ~256 GB of memory at 2‑bit precision

## Why it matters

Developers can now experiment with high‑capacity LLMs on their own hardware without needing cloud services.

## Sources & references

1. [NVIDIA Nemotron 3.5 + Meta Muse Spark Open](https://github.com/unslothai/unsloth/releases/tag/v0.1.908-beta) – Unsloth Releases, 2026-10-15

Last updated: 2026-10-15