Microsoft Foundry

About Microsoft Foundry

Kickstart innovation with Microsoft Foundry, the AI app and agent factory designed to accelerate AI-driven, cloud-native development across industries.

Website ↗Documentation ↗

Source ↗ · 2026-11-12T03:22:24.068797307Z

Service status

unknown

Current inference service status unverified

Official status page ↗

13,283 indexed models

13,283 matching models

Qwen/Qwen2-72B-Instruct

vertexAI/publishers/hf-qwen/models/qwen2-72b-instruct@001

Input modalities
text
Output modalities
text

Benchmarks

  • LiveBench: 33.548%
  • LMArena: 1,203.28
  • Open LLM Leaderboard v2: 43.594%

gpt-4 · azure-openai v0613

azureFoundry/azure-openai/gpt-4@0613

# This model can be deployed for inferencing. ## Model family: GPT-4 GPT-4 is a large multimodal model that accepts text or image inputs and outputs text. It can solve complex problems with greater accuracy than any of our previous models, thanks to its extensive general knowle

Input modalities
text
Output modalities
text

Benchmarks

  • LiveBench: 46.077%
  • LMArena: 1,186.013

Qwen/Qwen1.5-110B-Chat

vertexAI/publishers/hf-qwen/models/qwen1.5-110b-chat@001

Input modalities
text
Output modalities
text

Benchmarks

  • LiveBench: 20.918%
  • LMArena: 1,174.578
  • Open LLM Leaderboard v1: 68.006%
  • Open LLM Leaderboard v2: 33.127%

Qwen/Qwen1.5-72B-Chat

vertexAI/publishers/hf-qwen/models/qwen1.5-72b-chat@001

Benchmarks

  • LiveBench: 21.793%
  • LMArena: 1,166.159
  • Open LLM Leaderboard v1: 65.981%

Qwen/QwQ-32B-Preview

azureFoundry/azure-huggingface/qwen--qwq-32b-preview@5

Preview QwQ 32B reasoning model for experimental math and coding tasks.

Context window
32,768
Input modalities
text
Output modalities
text

Benchmarks

  • LiveBench: 30.582%
  • LLM Stats · GitHub archive: 0.906
  • LMArena: 1,161.8
  • Open LLM Leaderboard v2: 34.12%
  • Open Persian LLM Leaderboard: 87.24%

Qwen/Qwen1.5-32B-Chat

azureFoundry/HuggingFace/qwen-qwen1.5-32b-chat@1

`Qwen/Qwen1.5-32B-Chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/Qwen/Qwen1.5-32B-Chat) - [Text Generation Inference Documentation](https:

Input modalities
text
Output modalities
text

Benchmarks

  • LMArena: 1,137.209
  • Open LLM Leaderboard v1: 62.952%
  • Open LLM Leaderboard v2: 29.257%

Qwen/Qwen1.5-14B-Chat

azureFoundry/HuggingFace/qwen-qwen1.5-14b-chat@1

`Qwen/Qwen1.5-14B-Chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/Qwen/Qwen1.5-14B-Chat) - [Text Generation Inference Documentation](https:

Input modalities
text
Output modalities
text

Benchmarks

  • LMArena: 1,127.7
  • Open Ko-LLM Leaderboard: 42.873
  • Open LLM Leaderboard v1: 62.366%
  • Open LLM Leaderboard v2: 23.566%

deepseek-ai/deepseek-llm-67b-chat

vertexAI/publishers/hf-deepseek-ai/models/deepseek-llm-67b-chat@001

Input modalities
text
Output modalities
text

Benchmarks

  • LMArena: 1,105.035
  • Open LLM Leaderboard v1: 71.789%
  • Open LLM Leaderboard v2: 27.311%

Qwen/Qwen1.5-7B-Chat

vertexAI/publishers/hf-qwen/models/qwen1.5-7b-chat@001

Input modalities
text
Output modalities
text

Benchmarks

  • LiveBench: 11.624%
  • LMArena: 1,083.465
  • Open LLM Leaderboard v1: 55.155%
  • Open LLM Leaderboard v2: 17.621%

upstage/SOLAR-10.7B-Instruct-v1.0

vertexAI/publishers/hf-upstage/models/solar-10.7b-instruct-v1.0@001

Input modalities
text
Output modalities
text

Benchmarks

  • LMArena: 1,083.093
  • Open LLM Leaderboard v1: 74.201%
  • Open LLM Leaderboard v2: 20.572%

Qwen/Qwen1.5-4B-Chat

vertexAI/publishers/hf-qwen/models/qwen1.5-4b-chat@001

Input modalities
text
Output modalities
text

Benchmarks

  • LiveBench: 8.147%
  • LMArena: 997.239
  • Open LLM Leaderboard v1: 46.786%
  • Open LLM Leaderboard v2: 12.627%

012shin/KAIROS-ast-fake-audio-detection_unsupervised

azureFoundry/HuggingFace/012shin-kairos-ast-fake-audio-detection-unsupervised@1

`012shin/KAIROS-ast-fake-audio-detection_unsupervised` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/012shin/KAIROS-ast-fake-audio-detection_unsupervised) - [`audio-classification` Task on Hugging Face](https://huggingface.co/tasks/audi

01-ai/Yi-1.5-34B

azureFoundry/HuggingFace/01-ai-yi-1.5-34b@1

`01-ai/Yi-1.5-34B` powered by Text Generation Inference. - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/01-ai/Yi-1.5-34B) ### Send Request You can use cURL or any REST Client to sent req

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 73.505%
  • Open LLM Leaderboard v2: 25.646%

01-ai/Yi-1.5-34B-32K

azureFoundry/HuggingFace/01-ai-yi-1.5-34b-32k@1

`01-ai/Yi-1.5-34B-32K` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/01-ai/Yi-1.5-34B-32K) - [Text Generation Inference Documentation](https://

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 60.701%
  • Open LLM Leaderboard v2: 26.728%

01-ai/Yi-1.5-34B-Chat

vertexAI/publishers/hf-01-ai/models/yi-1.5-34b-chat@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 74.824%
  • Open LLM Leaderboard v2: 33.358%

01-ai/Yi-1.5-34B-Chat-16K

azureFoundry/HuggingFace/01-ai-yi-1.5-34b-chat-16k@1

`01-ai/Yi-1.5-34B-Chat-16K` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K) - [Text Generation Inference Documentation

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 73.57%
  • Open LLM Leaderboard v2: 29.404%

01-ai/Yi-1.5-6B

azureFoundry/HuggingFace/01-ai-yi-1.5-6b@1

`01-ai/Yi-1.5-6B` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/01-ai/Yi-1.5-6B) - [Text Generation Inference Documentation](https://huggingfac

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 61.6%
  • Open LLM Leaderboard v2: 16.746%

01-ai/Yi-1.5-6B-Chat

azureFoundry/HuggingFace/01-ai-yi-1.5-6b-chat@1

`01-ai/Yi-1.5-6B-Chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) - [Text Generation Inference Documentation](https://

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 66.167%
  • Open LLM Leaderboard v2: 22.784%

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace