# Ollama Local AI Runtimes v0.40.5-rc1: New model... (#19030)

> **Key Architectural Takeaway:** ci: shorten Windows Vulkan build path Keep the nested shader-generator compiler probes below Windows path limits in checkouts with longer repository names.

**Published:** 2026-10-15T14:28:26+00:00 
**Source:** Ollama Local AI Runtimes 
**Category:** ai-local-edge 
**Canonical URL:** https://fosswire.org/news/ollama-local-ai-runtimes-v0405-rc1-new-model-19030.html 

## Executive Summary
ci: shorten Windows Vulkan build path Keep the nested shader-generator compiler probes below Windows path limits in checkouts with longer repository names. mlx: fix Nemotron bugs and support global scales Accept published Nemotron layer names while retaining legacy aliases, and fix layer-count inference and detached MTP quantization. Stabilize Mamba softplus, preserve FP32 vision normalization, and compile Mamba gate and norm scaling.

## Architectural & Systems Analysis
From an artificial intelligence architecture, model weights governance, and inference efficiency perspective:

- **Weights Accessibility & Sovereignty:** Evaluates whether weights are open for private self-hosting or locked behind centralized cloud APIs.
- **Quantization & Edge Performance:** Kernel optimizations (4-bit/8-bit GGUF, AWQ, EXL2) allow high tokens-per-second on consumer GPUs and Apple Silicon.
- **Reasoning & Architectural Scaling:** Scrutinizes mixture-of-experts (MoE), attention mechanisms, and fine-tuning datasets against open community benchmarks.

## Impact on the Open Ecosystem
Protects developers and enterprises from proprietary black-box entrapment, fostering auditable, sovereign AI infrastructure.