Darkspyre.Inference.Tensor.LLM.Qwen
11.20.0
Prefix Reserved
dotnet add package Darkspyre.Inference.Tensor.LLM.Qwen --version 11.20.0
NuGet\Install-Package Darkspyre.Inference.Tensor.LLM.Qwen -Version 11.20.0
<PackageReference Include="Darkspyre.Inference.Tensor.LLM.Qwen" Version="11.20.0" />
<PackageVersion Include="Darkspyre.Inference.Tensor.LLM.Qwen" Version="11.20.0" />
<PackageReference Include="Darkspyre.Inference.Tensor.LLM.Qwen" />
paket add Darkspyre.Inference.Tensor.LLM.Qwen --version 11.20.0
#r "nuget: Darkspyre.Inference.Tensor.LLM.Qwen, 11.20.0"
#:package Darkspyre.Inference.Tensor.LLM.Qwen@11.20.0
#addin nuget:?package=Darkspyre.Inference.Tensor.LLM.Qwen&version=11.20.0
#tool nuget:?package=Darkspyre.Inference.Tensor.LLM.Qwen&version=11.20.0
Darkspyre.Inference.Tensor.LLM.Qwen
Text generation with Qwen-compatible GGUF models inside the application's process, through TensorSharp. The engine
implements Common's ILlmInference, so Darkspyre.Inference.Connect.SelfHost can serve it as a conversation
provider.
Install
dotnet add package Darkspyre.Inference.Tensor.LLM.Qwen --prerelease
Register
Construct QwenLlmInference, or call AddTensorEngines() from Darkspyre.Inference.Tensor.Registry, which registers
QwenEngineProvider. Qwen models arrive by import: the package has no built-in pack.
Example
Register the imported pack in the manager's catalog and install it through packs.InstallAsync(modelKey) when the
person chooses to acquire it. The following load uses that installed pack.
await using var qwen = new QwenLlmInference(packs, TensorBackendKind.Auto, scratchDirectory);
await qwen.StartAsync();
await qwen.LoadAsync(modelKey); // Accepts loading, not completion.
Subscribe to EngineStatusChanged before loading. After it reports Loaded, make requests; handle Failed instead of
sending a request after a failed load. Awaiting LoadAsync alone does not wait for Loaded.
LlmInferenceResult result = await qwen.CompleteAsync(new LlmInferenceRequest
{
ModelId = modelKey.ModelId,
Messages = [new LlmMessage("user", "Name three uses for a paperclip.")]
}, cancellationToken);
scratchDirectory is an absolute folder the application owns and empties before the engine runs; the engine writes
request images beneath it.
Settings
QwenSetup.CreateSettingsManager opens the engine's settings: the model with its install state, "Runs on", the fields
that import a model from a file, folder, URL or repository, and the download, check, load and backend-check actions.
Limits
- Automatic backend selection uses Metal, then GGML CPU, on macOS; CUDA, Vulkan, then GGML CPU elsewhere. CUDA is not offered on Windows ARM64. Apple MLX is a separate backend choice.
- Reasoning levels are
NoneandHigh. - Top-p, top-k and seed need a positive temperature. Stop sequences and penalties also work with greedy decoding.
- A
qwen3GGUF is reported as not supported. - The engine shares the process's one GGML runtime through
Darkspyre.Inference.Tensor.Ggml. - An application that stops reading a stream disposes its enumerator, so unloading can finish.
The Darkspyre.Inference packages
This package is one library of the Darkspyre.Inference family. The family runs AI inference from .NET applications through typed, provider-neutral contracts.
Darkspyre.Inference.Commonholds the contracts every other package shares: requests, results, capabilities, failures and the provider setup model.Darkspyre.Inference.Connect.Commonholds the conversation and embedding services. Each Connect provider package adds one provider, andAddLlmConnect()discovers every provider package the application references.- The Tensor packages load and run models inside the application's own process.
- The UI.Settings packages provide the setup editors a host places in its own window or page.
Every package of the family carries the same version. Reference all of them at the same version: each package depends on the exact version of the family packages it uses.
The packages are licensed under the MIT license. LICENSE.md in each package holds the license text.
| Package | Holds |
|---|---|
| Darkspyre.Inference.Common | Shared contracts for Connect and Tensor |
| Darkspyre.Inference.Connect | Image, speech and audio connectors |
| Darkspyre.Inference.Connect.Common | Conversation and embedding services and provider discovery |
| Darkspyre.Inference.Connect.Codex | Conversations on a ChatGPT subscription |
| Darkspyre.Inference.Connect.Claude | Conversations on a Claude subscription through the Claude CLI |
| Darkspyre.Inference.Connect.HostTools | The host-tools local service and its client |
| Darkspyre.Inference.Connect.Antigravity | Conversations on a Google subscription through the Antigravity CLI |
| Darkspyre.Inference.Connect.Grok | Conversations on a Grok subscription |
| Darkspyre.Inference.Connect.Anthropic | Conversations through the Anthropic API with an API key, with hosted web search |
| Darkspyre.Inference.Connect.OpenAiApi | Conversations and embeddings through the OpenAI API |
| Darkspyre.Inference.Connect.SelfHost | Conversations and embeddings on engines the application runs |
| Darkspyre.Inference.Tensor.Common | Model packs, the model lifecycle and the Tensor capability interfaces |
| Darkspyre.Inference.Tensor.Decision.Laya | Laya typed decisions through ONNX Runtime |
| Darkspyre.Inference.Tensor.Embedding | Text embeddings from GGUF sentence encoders |
| Darkspyre.Inference.Tensor.Embedding.Gemma | EmbeddingGemma text and image embeddings |
| Darkspyre.Inference.Tensor.Ggml | The process's GGML and MLX native runtime |
| Darkspyre.Inference.Tensor.Image.Supra | Supra2-IMG image generation |
| Darkspyre.Inference.Tensor.LLM.Qwen | Qwen GGUF text generation |
| Darkspyre.Inference.Tensor.Registry | Registration and discovery of the Tensor engines |
| Darkspyre.Inference.Tensor.STT.Whisper | Whisper speech transcription |
| Darkspyre.Inference.UI.Settings.Core | Editor state and host contracts both setup editors share |
| Darkspyre.Inference.UI.Settings.Avalonia | The Avalonia setup editor |
| Darkspyre.Inference.UI.Settings.Blazor | The Blazor setup editor |
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net11.0 is compatible. |
-
net11.0
- Darkspyre.Inference.Tensor.Common (= 11.20.0)
- Darkspyre.Inference.Tensor.Ggml (= 11.20.0)
- StbImageSharp (>= 2.30.15)
- TensorSharp.Backends.Cuda (>= 2026.10.11)
- TensorSharp.Backends.GGML (>= 2026.10.11)
- TensorSharp.Backends.MLX (>= 2026.10.11)
- TensorSharp.Chat (>= 2026.10.11)
- TensorSharp.Models (>= 2026.10.11)
- TensorSharp.Runtime (>= 2026.10.11)
- TensorSharp.Tensors (>= 2026.10.11)
NuGet packages (1)
Showing the top 1 NuGet packages that depend on Darkspyre.Inference.Tensor.LLM.Qwen:
| Package | Downloads |
|---|---|
|
Darkspyre.Inference.Tensor.Registry
Registration, validation and ordered discovery of the Darkspyre Tensor engine implementations. |
GitHub repositories
This package is not used by any popular GitHub repositories.
| Version | Downloads | Last Updated |
|---|---|---|
| 11.20.0 | 117 | 11/15/2026 |
| 11.19.4-rc.3 | 86 | 11/6/2026 |
| 11.19.3-rc.3 | 65 | 11/5/2026 |
| 11.19.3-rc.2 | 89 | 10/31/2026 |
| 11.17.3-rc.2 | 91 | 10/26/2026 |