Instructions to use SanctumAI/Phi-3.5-mini-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SanctumAI/Phi-3.5-mini-instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SanctumAI/Phi-3.5-mini-instruct-GGUF",
	filename="phi-3.5-mini-instruct.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SanctumAI/Phi-3.5-mini-instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SanctumAI/Phi-3.5-mini-instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SanctumAI/Phi-3.5-mini-instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SanctumAI/Phi-3.5-mini-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M

Ollama
How to use SanctumAI/Phi-3.5-mini-instruct-GGUF with Ollama:
```
ollama run hf.co/SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use SanctumAI/Phi-3.5-mini-instruct-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SanctumAI/Phi-3.5-mini-instruct-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SanctumAI/Phi-3.5-mini-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SanctumAI/Phi-3.5-mini-instruct-GGUF to start chatting

Docker Model Runner
How to use SanctumAI/Phi-3.5-mini-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M
```

Lemonade

How to use SanctumAI/Phi-3.5-mini-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SanctumAI/Phi-3.5-mini-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Phi-3.5-mini-instruct-GGUF-Q4_K_M

List all available models

lemonade list

This model was quantized by SanctumAI. To leave feedback, join our community in Discord.

Phi 3 Mini 4K Instruct GGUF

Model creator: microsoft
Original model: Phi-3.5-mini-instruct

Model Summary:

Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.

Prompt Template:

If you're using Sanctum app, simply use Phi 3 model preset.

Prompt template:

<|system|>
{system_prompt}<|end|>
<|user|>
{prompt}<|end|>
<|assistant|>

Hardware Requirements Estimate

Name	Quant method	Size	Memory (RAM, vRAM) required
phi-3.5-mini-instruct.Q2_K.gguf	Q2_K	1.42 GB	5.02 GB
phi-3.5-mini-instruct.Q3_K_S.gguf	Q3_K_S	1.68 GB	5.27 GB
phi-3.5-mini-instruct.Q3_K_M.gguf	Q3_K_M	1.96 GB	5.52 GB
phi-3.5-mini-instruct.Q3_K_L.gguf	Q3_K_L	2.09 GB	5.65 GB
phi-3.5-mini-instruct.Q4_0.gguf	Q4_0	2.18 GB	5.73 GB
phi-3.5-mini-instruct.Q4_K_S.gguf	Q4_K_S	2.19 GB	5.74 GB
phi-3.5-mini-instruct.Q4_K_M.gguf	Q4_K_M	2.39 GB	5.93 GB
phi-3.5-mini-instruct.Q4_K.gguf	Q4_K	2.39 GB	5.93 GB
phi-3.5-mini-instruct.Q4_1.gguf	Q4_1	2.41 GB	5.94 GB
phi-3.5-mini-instruct.Q5_0.gguf	Q5_0	2.64 GB	6.16 GB
phi-3.5-mini-instruct.Q5_K_S.gguf	Q5_K_S	2.64 GB	6.16 GB
phi-3.5-mini-instruct.Q5_K_M.gguf	Q5_K_M	2.82 GB	6.32 GB
phi-3.5-mini-instruct.Q5_K.gguf	Q5_K	2.82 GB	6.32 GB
phi-3.5-mini-instruct.Q5_1.gguf	Q5_1	2.87 GB	6.38 GB
phi-3.5-mini-instruct.Q6_K.gguf	Q6_K	3.14 GB	6.62 GB
phi-3.5-mini-instruct.Q8_0.gguf	Q8_0	4.06 GB	7.48 GB
phi-3.5-mini-instruct.f16.gguf	f16	7.64 GB	10.82 GB

Disclaimer

Sanctum is not the creator, originator, or owner of any Model featured in the Models section of the Sanctum application. Each Model is created and provided by third parties. Sanctum does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Model listed there. You understand that supported Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Model is the sole responsibility of the person or entity who originated such Model. Sanctum may not monitor or control the Models supported and cannot, and does not, take responsibility for any such Model. Sanctum disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Models. Sanctum further disclaims any warranty that the Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Models, your downloading of any Model, or use of any other Model provided by or through Sanctum.

Downloads last month: 850

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit