Skip to content

Update Foundry models #15389

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
joperezr merged 1 commit into from
Mar 19, 2026
Merged

Update Foundry models #15389

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 12 additions & 2 deletions src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ public static partial class Anthropic
public static readonly FoundryModel ClaudeOpus45 = new() { Name = "claude-opus-4-5", Version = "20251101", Format = "Anthropic" };

/// <summary>
/// Claude Opus 4.6 is the latest version of Anthropic's most intelligent model, and the world's best model for coding, enterprise agents, and professional work. With a 1M token context window (beta) and 128K max output, Opus 4.6 is ideal for production code,
/// Claude Opus 4.6 is the latest version of Anthropic's most intelligent model, and the world's best model for coding, enterprise agents, and professional work. With a 1M token context window and 128K max output, Opus 4.6 is ideal for production code, sophist
/// </summary>
Comment on lines 46 to 48
public static readonly FoundryModel ClaudeOpus46 = new() { Name = "claude-opus-4-6", Version = "1", Format = "Anthropic" };

Expand All @@ -54,7 +54,7 @@ public static partial class Anthropic
public static readonly FoundryModel ClaudeSonnet45 = new() { Name = "claude-sonnet-4-5", Version = "20250929", Format = "Anthropic" };

/// <summary>
/// Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows. With a 1M token context window (beta) and 128K max output, Sonnet 4.6 is ideal for coding, agents, office tasks, financial analysis, cybersecurity
/// Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows. With a 1M token context window and 128K max output, Sonnet 4.6 is ideal for coding, agents, office tasks, financial analysis, cybersecurity, and c
Copy link
Copy Markdown
Contributor Author

@sebastienros sebastienros Mar 19, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@JamesNK you added the markdown formatting, so I know you are familiar with these files generation. If I don't find time to look into it (super low priority) then it'd be interesting to check if we have a limit for these blobs (it's truncated) and if we want to bump it.

/// </summary>
Comment on lines 56 to 58
public static readonly FoundryModel ClaudeSonnet46 = new() { Name = "claude-sonnet-4-6", Version = "1", Format = "Anthropic" };
}
Expand Down Expand Up @@ -2785,6 +2785,16 @@ public static partial class OpenAI
/// </summary>
public static readonly FoundryModel Gpt54 = new() { Name = "gpt-5.4", Version = "2026-03-05", Format = "OpenAI" };

/// <summary>
/// GPT‑5.4‑mini is a compact, cost‑efficient model designed for reliable performance across high‑volume, everyday AI workloads.
/// </summary>
public static readonly FoundryModel Gpt54Mini = new() { Name = "gpt-5.4-mini", Version = "2026-03-17", Format = "OpenAI" };

/// <summary>
/// GPT‑5.4‑nano is a lightweight, ultra‑efficient model designed for low‑latency, cost‑effective tasks at massive scale.
/// </summary>
public static readonly FoundryModel Gpt54Nano = new() { Name = "gpt-5.4-nano", Version = "2026-03-17", Format = "OpenAI" };

/// <summary>
/// GPT‑5.4-Pro is OpenAI’s most capable frontier model, built to deliver faster, more reliable results for complex professional work.
/// </summary>
Expand Down
134 changes: 133 additions & 1 deletion src/Aspire.Hosting.Foundry/FoundryModel.Local.Generated.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -896,7 +896,95 @@ public static partial class Local
/// </para>
/// <para>See Hugging Face model <see href="https://huggingface.co/Qwen/Qwen3-0.6B">Qwen3-0.6B</see> for details.</para>
/// </summary>
public static readonly FoundryModel Qwen306b = new() { Name = "qwen3-0.6b", Version = "2", Format = "Microsoft" };
public static readonly FoundryModel Qwen306b = new() { Name = "qwen3-0.6b", Version = "1", Format = "Microsoft" };

/// <summary>
/// <para>This model is an optimized version of Qwen3-1.7B to enable local inference. This model uses KLD Gradient quantization.</para>
/// <para>
/// <b>Model Description</b>
/// </para>
/// <list type="bullet">
/// <item>
/// <description>
/// <para>
/// <b>Developed by:</b> Microsoft</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Model type:</b> ONNX</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>License:</b> apache-2.0</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Model Description:</b> This is a conversion of the Qwen3-1.7B for local inference.</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Disclaimer:</b> Model is only an optimization of the base model, any risk associated with the model is the responsibility of the user of the model. Please verify and test for your scenarios. There may be a slight difference in output from the base model with the optimizations applied. Note that optimizations applied are distinct from fine tuning and thus do not alter the intended uses or capabilities of the model.</para>
/// </description>
/// </item>
/// </list>
/// <para>
/// <b>Base Model Information</b>
/// </para>
/// <para>See Hugging Face model <see href="https://huggingface.co/Qwen/Qwen3-1.7B">Qwen3-1.7B</see> for details.</para>
/// </summary>
public static readonly FoundryModel Qwen317b = new() { Name = "qwen3-1.7b", Version = "1", Format = "Microsoft" };

/// <summary>
/// <para>This model is an optimized version of Qwen3-14B to enable local inference. This model uses GPTQ quantization.</para>
/// <para>
/// <b>Model Description</b>
/// </para>
/// <list type="bullet">
/// <item>
/// <description>
/// <para>
/// <b>Developed by:</b> Microsoft</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Model type:</b> ONNX</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>License:</b> apache-2.0</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Model Description:</b> This is a conversion of the Qwen3-14B for local inference.</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Disclaimer:</b> Model is only an optimization of the base model, any risk associated with the model is the responsibility of the user of the model. Please verify and test for your scenarios. There may be a slight difference in output from the base model with the optimizations applied. Note that optimizations applied are distinct from fine tuning and thus do not alter the intended uses or capabilities of the model.</para>
/// </description>
/// </item>
/// </list>
/// <para>
/// <b>Base Model Information</b>
/// </para>
/// <para>See Hugging Face model <see href="https://huggingface.co/Qwen/Qwen3-14B">Qwen3-14B</see> for details.</para>
/// </summary>
public static readonly FoundryModel Qwen314b = new() { Name = "qwen3-14b", Version = "1", Format = "Microsoft" };

/// <summary>
/// <para>This model is an optimized version of Qwen3-4B to enable local inference. This model uses KLD Gradient quantization.</para>
Expand Down Expand Up @@ -942,6 +1030,50 @@ public static partial class Local
/// </summary>
public static readonly FoundryModel Qwen34b = new() { Name = "qwen3-4b", Version = "1", Format = "Microsoft" };

/// <summary>
/// <para>This model is an optimized version of Qwen3-8B to enable local inference. This model uses KLD Gradient quantization.</para>
/// <para>
/// <b>Model Description</b>
/// </para>
/// <list type="bullet">
/// <item>
/// <description>
/// <para>
/// <b>Developed by:</b> Microsoft</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Model type:</b> ONNX</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>License:</b> apache-2.0</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Model Description:</b> This is a conversion of the Qwen3-8B for local inference.</para>
/// </description>
/// </item>
/// <item>
/// <description>
/// <para>
/// <b>Disclaimer:</b> Model is only an optimization of the base model, any risk associated with the model is the responsibility of the user of the model. Please verify and test for your scenarios. There may be a slight difference in output from the base model with the optimizations applied. Note that optimizations applied are distinct from fine tuning and thus do not alter the intended uses or capabilities of the model.</para>
/// </description>
/// </item>
/// </list>
/// <para>
/// <b>Base Model Information</b>
/// </para>
/// <para>See Hugging Face model <see href="https://huggingface.co/Qwen/Qwen3-8B">Qwen3-8B</see> for details.</para>
/// </summary>
public static readonly FoundryModel Qwen38b = new() { Name = "qwen3-8b", Version = "1", Format = "Microsoft" };

/// <summary>
/// <para>This model is an optimized version of Qwen3-VL-2B-Instruct to enable local inference. This model uses RTN quantization.</para>
/// <para>
Expand Down
Loading