Instructions to use tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF",
	filename="Phi-3-mini-4k-instruct-dequantized-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 tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K

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 tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K

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 tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/Phi-3-mini-4k-instruct-dequantized-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": "tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K

Ollama
How to use tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF with Ollama:
```
ollama run hf.co/tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/Phi-3-mini-4k-instruct-dequantized-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 tensorblock/Phi-3-mini-4k-instruct-dequantized-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 tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF to start chatting

Docker Model Runner
How to use tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K
```

Lemonade

How to use tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/Phi-3-mini-4k-instruct-dequantized-GGUF:Q2_K

Run and chat with the model

lemonade run user.Phi-3-mini-4k-instruct-dequantized-GGUF-Q2_K

List all available models

lemonade list

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c398f27d6beecc43a389e5e85603362aee01a40394c6613665213dcf9d22b91a
-size 2087597056

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e34c80fa31bb71d43718f7554d2358828a4fc5f2b99f306ceb73bcbf547e38ca
-size 1955476480

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bba28cdc03b6862529b9d25703d84e94e998af9afb0e75f55f41dcc853d9a6d1
-size 1681798144

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5895d0d467829bb1789f99f76ba2dc5195901a34d3441df41399f0fc2818bfb2
-size 2176176640

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:21d4ccca9babda4d71325845f00824e4719d4c5a76483b5dc9475bb5d81d4942
-size 2393231872

tensorblock
/

Phi-3-mini-4k-instruct-dequantized-GGUF

Remove .gguf files (keep Q2_K.gguf)