ElBruno.LocalLLMs.BitNet 0.20.1

ElBruno.LocalLLMs

Run local LLMs in .NET through IChatClient 🧠

Run local LLMs in .NET through IChatClient — the same interface you'd use for Azure OpenAI, Ollama, or any other provider. Powered by ONNX Runtime GenAI and BitNet.

What's New

• 📦 Transitive native runtime fix (v0.20.1) — Added buildTransitive packaging so onnxruntime-genai.dll is copied for downstream consumers that reference ElBruno.LocalLLMs transitively (Issue #24).
• 🤖 Qwen3 & MagenticBrain support (v0.20.0) — New ChatTemplateFormat.Qwen3 formatter and KnownModels.MagenticBrain / KnownModels.Qwen3_14BInstruct for agentic multi-agent orchestration loops.
• 👁️ Fara 1.5-9B vision-language model (v0.20.0) — Run Microsoft's Fara VLM locally via the new LocalVisionChatClient, IVisionGenerationModel, and VisionChatOptions with image paths.
• 🌐 ElBruno.MagenticUI reference app — Full Blazor Server multi-agent app (FileSurfer, WebFetcher, Coder, UserProxy) powered by this library. Drop-in .NET port of microsoft/magentic-ui with human-in-the-loop support.
• 📡 OpenTelemetry diagnostics (v0.19.0) — Generation lifecycle activities and metrics (gen_ai.client.*) via ActivitySource + Meter both named ElBruno.LocalLLMs.
• ✅ Gemma 4 family active — E2B, E4B, 12B Unified, 26B-A4B, 31B all supported via conversion workflows.
• ⬆️ ONNX Runtime GenAI 0.14.1 — upgraded across library, tests, samples, and benchmarks.

Features

• 🔌 IChatClient implementation — seamless integration with Microsoft.Extensions.AI
• 📦 Automatic model download — models are fetched from HuggingFace on first use
• 🚀 Zero friction — works out of the box with sensible defaults (Phi-3.5 mini)
• 🖥️ Multi-hardware — CPU, CUDA, and DirectML execution providers
• 💉 DI-friendly — register with AddLocalLLMs() or AddBitNetChatClient() in ASP.NET Core
• 🔄 Streaming — token-by-token streaming via GetStreamingResponseAsync
• 📊 Multi-model — switch between Phi-3.5, Phi-4, Qwen2.5, Qwen3, Llama 3.2, MagenticBrain, and more
• 👁️ Vision-language models — run Fara 1.5-9B image+text models via LocalVisionChatClient
• 🤖 Agentic models — Qwen3 / MagenticBrain support for multi-agent orchestration loops
• 🎯 Fine-tuned models — pre-trained Qwen2.5 variants for tool calling and RAG (guide)
• ⚡ BitNet support — run 1.58-bit ternary models via bitnet.cpp with extreme efficiency (guide)
• 📈 OpenTelemetry diagnostics — lifecycle activities and metrics for queued, first-token, completion, cancellation, and failure (guide)

Packages

Package	NuGet	Downloads	Description
ElBruno.LocalLLMs			Core library — ONNX Runtime GenAI models via IChatClient
ElBruno.LocalLLMs.Rag			RAG pipeline — document chunking, indexing, retrieval
ElBruno.LocalLLMs.BitNet			BitNet 1.58-bit models via bitnet.cpp + IChatClient

Installation

dotnet add package ElBruno.LocalLLMs

For CPU scenarios, no extra package is required — the transitive buildTransitive shim copies onnxruntime-genai.dll automatically on Windows.

Add a runtime package only when you want a specific GPU provider:

# 🟢 NVIDIA GPU (CUDA):
dotnet add package Microsoft.ML.OnnxRuntimeGenAI.Cuda

# 🔵 Any Windows GPU — AMD, Intel, NVIDIA (DirectML):
dotnet add package Microsoft.ML.OnnxRuntimeGenAI.DirectML

⚠️ Add at most one GPU runtime package. Do not reference both Microsoft.ML.OnnxRuntimeGenAI.Cuda and Microsoft.ML.OnnxRuntimeGenAI.DirectML simultaneously.

If you use a GPU runtime package and want to disable the transitive CPU copy shim, set: <ElBrunoLocalLLMsDisableCpuNativeCopy>true</ElBrunoLocalLLMsDisableCpuNativeCopy> in your application .csproj.

🚀 The library defaults to ExecutionProvider.Auto — it tries GPU first and falls back to CPU automatically. No code changes needed.

Quick Start

using ElBruno.LocalLLMs;
using Microsoft.Extensions.AI;

// Create a local chat client (downloads Phi-3.5 mini on first run)
using var client = await LocalChatClient.CreateAsync();

var response = await client.GetResponseAsync([
    new(ChatRole.User, "What is the capital of France?")
]);

Console.WriteLine(response.Text);

First Run

The first time you create a LocalChatClient, the model is downloaded from HuggingFace to your local cache directory (~2-4 GB). This typically takes 30-60 seconds depending on your internet connection.

Track download progress:

using var client = await LocalChatClient.CreateAsync(
    new LocalLLMsOptions { Model = KnownModels.Phi35MiniInstruct },
    progress: new Progress<ModelDownloadProgress>(p =>
    {
        var percent = (p.BytesDownloaded * 100) / p.TotalBytes;
        Console.WriteLine($"{p.FileName}: {percent:F1}%");
    })
);

Subsequent runs load instantly from cache (%LOCALAPPDATA%/ElBruno/LocalLLMs/models).

Skip auto-download if using a pre-downloaded model:

var options = new LocalLLMsOptions
{
    Model = KnownModels.Phi35MiniInstruct,
    ModelPath = "/path/to/local/model",
    EnsureModelDownloaded = false
};
using var client = await LocalChatClient.CreateAsync(options);

Streaming

using ElBruno.LocalLLMs;
using Microsoft.Extensions.AI;

using var client = await LocalChatClient.CreateAsync(new LocalLLMsOptions
{
    Model = KnownModels.Phi35MiniInstruct
});

await foreach (var update in client.GetStreamingResponseAsync([
    new(ChatRole.System, "You are a helpful assistant."),
    new(ChatRole.User, "Explain quantum computing in simple terms.")
]))
{
    Console.Write(update.Text);
}

GPU Acceleration

By default, ExecutionProvider.Auto tries GPU first (CUDA → DirectML) and falls back to CPU automatically:

// Use explicit GPU provider (fails if CUDA not installed; use Auto to fallback to CPU)
var options = new LocalLLMsOptions
{
    ExecutionProvider = ExecutionProvider.Cuda
};

// Multi-GPU systems: select device ID
var options2 = new LocalLLMsOptions
{
    ExecutionProvider = ExecutionProvider.Cuda,
    GpuDeviceId = 1  // Use second GPU
};

Auto fallback behavior:

• CUDA available → uses NVIDIA GPU
• CUDA unavailable, DirectML available → uses AMD/Intel Arc GPU
• GPU unavailable → falls back to CPU (no errors, just slower)

See Troubleshooting: GPU Setup for debugging GPU issues.

Model Metadata

Inspect model capabilities at runtime — context window size, model name, and vocabulary:

using var client = await LocalChatClient.CreateAsync();

var metadata = client.ModelInfo;
Console.WriteLine($"Model:          {metadata?.ModelName}");
Console.WriteLine($"Context window: {metadata?.MaxSequenceLength}");
Console.WriteLine($"Vocab size:     {metadata?.VocabSize}");

This is useful for prompt-length validation, adaptive chunking, and model selection logic.

Dependency Injection

builder.Services.AddLocalLLMs(options =>
{
    options.Model = KnownModels.Phi35MiniInstruct;
    options.ExecutionProvider = ExecutionProvider.DirectML;
});

// Inject IChatClient anywhere
public class MyService(IChatClient chatClient) { ... }

Error Handling

The library provides structured exception types for graceful error handling:

using ElBruno.LocalLLMs;
using Microsoft.Extensions.AI;

try
{
    using var client = await LocalChatClient.CreateAsync();
    var response = await client.GetResponseAsync([
        new(ChatRole.User, "Your question here")
    ]);
}
catch (ExecutionProviderException ex)
{
    // GPU/provider-specific error (no CUDA, DirectML not available, etc.)
    Console.WriteLine($"Provider error: {ex.Message}");
}
catch (ModelCapacityExceededException ex)
{
    // Prompt/response too long for model's context window
    Console.WriteLine($"Capacity error: {ex.Message}");
    // Solution: use a larger model or truncate the prompt
}
catch (InvalidOperationException ex)
{
    // General operation error (model not found, download failed, etc.)
    Console.WriteLine($"Operation error: {ex.Message}");
}

Observability

LocalChatClient emits generation lifecycle diagnostics through ActivitySource and Meter, both named ElBruno.LocalLLMs.

using ElBruno.LocalLLMs.Diagnostics;

builder.Services.AddOpenTelemetry()
    .WithTracing(tracing => tracing.AddSource(LocalLLMsInstrumentation.ActivitySourceName))
    .WithMetrics(metrics => metrics.AddMeter(LocalLLMsInstrumentation.MeterName));

By default, telemetry excludes prompt and completion text. Opt in only when you want content attached:

var options = new LocalLLMsOptions
{
    CaptureTelemetryContent = true
};

See docs/observability.md for the lifecycle event contract, metric names, and Aspire wiring notes, and docs/cancellation.md for voice barge-in cancellation behavior.

Troubleshooting

GPU not working? Use ExecutionProvider.Cpu explicitly. See GPU Setup Validation.

Out of memory? Try a smaller model:

var options = new LocalLLMsOptions
{
    Model = KnownModels.Qwen25_05BInstruct  // 0.5B instead of 3.8B
};

Model download fails?

• Check your internet connection
• For private HuggingFace models, set the HF_TOKEN environment variable

For detailed troubleshooting, see docs/troubleshooting-guide.md.

Supported Models

🔄 Convert = Use the conversion scripts in scripts/ to export ONNX locally before running the model.

¹ MagenticBrain ONNX: No official ONNX yet. Use onnx-community/Qwen3-14B-ONNX as drop-in until Microsoft publishes a native conversion.

² Fara 1.5-9B ONNX: Convert via ORT-GenAI model builder (--model_type qwen_vl). Use LocalVisionChatClient (not LocalChatClient). See ONNX Conversion — Fara.

Fine-Tuned Models

Pre-trained variants optimized for specific tasks. A fine-tuned 0.5B model often matches or exceeds a base 1.5B on its specialized task.

See the Supported Models Guide for detailed model cards, performance benchmarks, and selection guidance.

Samples

🌐 Reference App: ElBruno.MagenticUI — full Blazor Server port of microsoft/magentic-ui running locally with this library.

Requirements

• .NET 8.0 or .NET 10.0
• CPU (default), NVIDIA GPU (CUDA), or Windows GPU (DirectML)
• ~2-8 GB disk space per model (depending on size and quantization)

Building from Source

git clone https://github.com/elbruno/ElBruno.LocalLLMs.git
cd ElBruno.LocalLLMs
dotnet restore ElBruno.LocalLLMs.slnx
dotnet build ElBruno.LocalLLMs.slnx
dotnet test ElBruno.LocalLLMs.slnx --framework net8.0

Documentation

• Getting Started — installation, first steps, configuration
• Supported Models — full model reference with tiers, specs, decision tree
• BitNet Guide — setup and usage of 1.58-bit BitNet models
• Cancellation Guide — streaming cancellation semantics and voice barge-in usage
• Observability — OpenTelemetry, lifecycle events, metrics, Aspire wiring
• Architecture — design decisions and internal structure
• Samples Guide — walkthrough of each sample application
• Benchmarks — how to run and interpret performance benchmarks
• Fine-Tuning Guide — using and training fine-tuned models
• ONNX Conversion — converting HuggingFace models to ONNX format
• ONNX Conversion — Fara VLM — converting Fara 1.5-9B vision-language model
• Publishing — NuGet package publishing with OIDC
• Contributing — how to contribute
• Changelog — version history

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

This project is licensed under the MIT License — see the LICENSE file for details.

👋 About the Author

Hi! I'm ElBruno 🧡, a passionate developer and content creator exploring AI, .NET, and modern development practices.

Made with ❤️ by ElBruno

If you like this project, consider following my work across platforms:

• 📻 Podcast: No Tienen Nombre — Spanish-language episodes on AI, development, and tech culture
• 💻 Blog: ElBruno.com — Deep dives on embeddings, RAG, .NET, and local AI
• 📺 YouTube: youtube.com/elbruno — Demos, tutorials, and live coding
• 🔗 LinkedIn: @elbruno — Professional updates and insights
• 𝕏 Twitter: @elbruno — Quick tips, releases, and tech news

🙏 Acknowledgments

• ONNX Runtime GenAI — inference engine
• BitNet / bitnet.cpp — 1.58-bit ternary model inference
• Microsoft.Extensions.AI — IChatClient interface
• Hugging Face — model hosting and community