# Phi-Ground-Any

[Canonical model page](https://headlessthrones.com/models/microsoft-phi-ground-any) · [Model library](https://headlessthrones.com/models)

Public catalog reference from Headless Thrones. Exact catalog ID: `microsoft-phi-ground-any`. Catalog source-check date: 2026-10-23.

This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial.

Current catalog answers

## What to know about Phi-Ground-Any

AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.

[Exact model](https://headlessthrones.com/models/microsoft-phi-ground-any#model-answer-identity) · [Access](https://headlessthrones.com/models/microsoft-phi-ground-any#model-answer-access) · [Inputs &amp; outputs](https://headlessthrones.com/models/microsoft-phi-ground-any#model-answer-modalities) · [License](https://headlessthrones.com/models/microsoft-phi-ground-any#model-answer-license) · [Model details](https://headlessthrones.com/models/microsoft-phi-ground-any#model-answer-research) · [Weight details](https://headlessthrones.com/models/microsoft-phi-ground-any#model-answer-repository)

### Which Phi-Ground-Any does this page describe?

Phi-Ground-Any is a model record from **Microsoft** in the Phi family. [Source](https://huggingface.co/microsoft/Phi-Ground-Any)

A separate version identifier is not documented in this record; the model name alone does not establish which snapshot a service runs.

### How can you access Phi-Ground-Any?

The catalog documents **Open weights** access  for Phi-Ground-Any. [Source](https://huggingface.co/microsoft/Phi-Ground-Any)

As of the catalog check, this version was listed without confirmed general availability. [Source](https://huggingface.co/microsoft/Phi-Ground-Any)

Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement.

### What can Phi-Ground-Any receive and generate?

Documented inputs: **Text and Image**. [Source](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/README.md)

Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.

### What license is recorded for Phi-Ground-Any?

The recorded license label is **mit**. [Source](https://huggingface.co/microsoft/Phi-Ground-Any)

Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.

### What distinguishes Phi-Ground-Any?

These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results.

**Screen grounding purpose**: Vision-language checkpoint fine-tuned from Phi 3.5 Vision Instruct for screen grounding. [Source](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/README.md)

**Required image geometry**: Requires fixed 1680x1008 input image resolution. [Source](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/README.md)

**Coordinate format**: Uses relative click coordinates on a 0–10,000 scale over the padded canvas. [Source](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/README.md)

**Structured grounding output**: Returns a click point as x/y tags with coordinates on a 0–10,000 scale over the padded image. [Source](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/README.md)

### What is documented about the Phi-Ground-Any checkpoint?

This evidence refers to `microsoft/Phi-Ground-Any` at recorded revision `081399127fd191906edf46a98f3d8d5193e328c2`, checked October 23, 2026. [Repository metadata](https://huggingface.co/api/models/microsoft/Phi-Ground-Any)

Recorded architecture class: `Phi3VForCausalLM`. [Repository metadata](https://huggingface.co/api/models/microsoft/Phi-Ground-Any)

Repository access gate: `false`. This records the repository's gate setting when checked; licensing and use terms still apply. [Repository metadata](https://huggingface.co/api/models/microsoft/Phi-Ground-Any)

#### What the configuration file says

The pinned `config.json` contains these values. [Pinned configuration](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/config.json)

`max_position_embeddings`: 131,072

`sliding_window`: 262,144

`torch_dtype`: bfloat16

`num_attention_heads`: 32

`num_key_value_heads`: 32

`num_hidden_layers`: 32

`hidden_size`: 3,072

Configuration values describe the checkpoint and its implementation. In particular, max\_position\_embeddings, sliding\_window and rope\_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior.

Read the retrieved model card for setup and qualifications. [Model card](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/README.md)

**Catalog qualifications:** Official publisher model repository; listed status confirms a catalog entry, not a verified hosted API service. [Source 1](https://huggingface.co/api/models/microsoft/Phi-Ground-Any) · [Source 2](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/README.md) · [Source 3](https://huggingface.co/microsoft/Phi-Ground-Any/resolve/081399127fd191906edf46a98f3d8d5193e328c2/config.json)

**Evidence still missing here:** context or input capacity, knowledge and training-data cutoffs, and tested hardware requirements. Missing documentation is not evidence that a feature is unavailable.

Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model.

Keep the exact version in view

## Other Phi models from Microsoft.

These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.

### [Phi-4-reasoning-vision-15B](https://headlessthrones.com/models/microsoft-phi-4-reasoning-vision-15b)

Open weights · 16,384 context tokens

### [Phi-4-mini-flash-reasoning](https://headlessthrones.com/models/microsoft-phi-4-mini-flash-reasoning)

Open weights · 64,000 context tokens

### [Phi-4-reasoning](https://headlessthrones.com/models/microsoft-phi-4-reasoning)

Open weights · 32,000 context tokens

### [Phi-4-reasoning-plus](https://headlessthrones.com/models/microsoft-phi-4-reasoning-plus)

Open weights · 32,000 context tokens

### [Phi-4-mini-reasoning](https://headlessthrones.com/models/microsoft-phi-4-mini-reasoning)

Open weights · 128,000 context tokens

### [Phi-4-mini-instruct](https://headlessthrones.com/models/microsoft-phi-4-mini-instruct)

Open weights · 128,000 context tokens
