LocalLLaMA warmed to Open WebUI Desktop because it kills the usual setup tax: no Docker, no terminal, local models if you want them, remote servers if you do not. The first pushback came fast too, with power users already asking for a slimmer build without bundled engines.
GitHub said on April 7, 2026 that Copilot CLI can now use a developer’s own model provider or fully local models. The change adds Azure OpenAI, Anthropic, offline mode, and optional GitHub auth while keeping the same agentic terminal workflow.
GitHub Changelog's April 7, 2026 X post said Copilot CLI can now connect to Azure OpenAI, Anthropic, and other OpenAI-compatible endpoints, or run fully local models instead of GitHub-hosted routing. GitHub's changelog adds that offline mode disables telemetry, unauthenticated use is possible with provider credentials alone, and built-in sub-agents inherit the chosen provider.
A LocalLLaMA user compared Gemma 4 31B, Gemma 4 26B-A4B, and Qwen 3.5 27B across 30 blind prompts judged by Claude Opus 4.6. The result is not one clear winner but a more useful trade-off story around reliability, verbosity, and category-specific strengths.
Ollama said on March 26, 2026 that VS Code now integrates with Ollama via GitHub Copilot. Ollama docs say VS Code 1.113+, GitHub Copilot Chat 0.41.0+, and Ollama v0.18.3+ let users load local or cloud Ollama models into the Copilot model picker, with GitHub Copilot Free sufficient for custom model selection.
A high-scoring LocalLLaMA post highlights Open WebUI’s Open Terminal: a Docker or bare-metal execution layer that lets local models run commands, edit files, and return artifacts through chat.