PulseAugur
EN
LIVE 01:34:36

Ollama updates boost local AI inference with Nemotron 3.5 and Muse Glimmer support

By PulseAugur Editorial · [2 sources] ·

Ollama has released new versions, v0.32.10 and v0.32.9, introducing performance enhancements and support for new open-weight models. Version v0.32.10 improves speculative decoding by defaulting the repeat_penalty to 1.0, aligning with other inference engines and speeding up local model execution. Both versions add support for NVIDIA's Nemotron 3.5 Lightning, a 30B mixture-of-experts model designed for AI agents, and Meta's Muse Glimmer multimodal model, with v0.32.7 specifically optimizing Muse Glimmer for Apple Silicon via the MLX engine. Additionally, the Muse Glimmer model is now available in GGUF format, making it more accessible for consumer GPUs. AI

IMPACT Enhances local AI development and experimentation by making powerful open-weight models more accessible and performant on consumer hardware.

RANK_REASON Updates to Ollama, a tool for running LLMs locally, including support for new models and performance improvements.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Ollama updates boost local AI inference with Nemotron 3.5 and Muse Glimmer support

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Updates to Ollama, a tool for running LLMs locally, including support for new models and performance improvements.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
63 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. dev.to — LLM tag TIER_1 English(EN) · soy ·

    Ollama v0.32.10 Speeds Up Speculative Decoding — Plus Nemotron 3.5 & AMD GPU Ops

    <p>Today's digest highlights Ollama v0.32.10, bringing faster speculative decoding, alongside NVIDIA's new Nemotron 3.5 Lightning open-weight model for agents. Additionally, AMD released GPU Operator v1.5.0 with key Kubernetes enhancements, and new GGUF models are trending.</p> <…

  2. dev.to — LLM tag TIER_1 English(EN) · soy ·

    Ollama v0.32.9 Integrates Nemotron 3.5 — Plus vLLM, JetPack, & AMD MoE

    <p>Today brings significant advancements in AI, led by Ollama v0.32.9's integration of NVIDIA Nemotron 3.5 Lightning. We also cover vLLM v0.27.0, a new AMD Mixture-of-Experts model, further Ollama updates, and NVIDIA's latest agentic AI tools and JetPack release.</p> <h2> Local A…

RELATED ENTITIES

RELATED TOPICS