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

Libraries

How to use Dhptl/Phi-3-mini-4k-instruct-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Dhptl/Phi-3-mini-4k-instruct-GGUF", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Dhptl/Phi-3-mini-4k-instruct-GGUF", trust_remote_code=True, dtype="auto")

llama-cpp-python

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Dhptl/Phi-3-mini-4k-instruct-GGUF",
	filename="Phi-3-mini-4k-instruct-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Dhptl/Phi-3-mini-4k-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 Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Dhptl/Phi-3-mini-4k-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 Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Dhptl/Phi-3-mini-4k-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 Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Dhptl/Phi-3-mini-4k-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 Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M

SGLang

How to use Dhptl/Phi-3-mini-4k-instruct-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Dhptl/Phi-3-mini-4k-instruct-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dhptl/Phi-3-mini-4k-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Dhptl/Phi-3-mini-4k-instruct-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dhptl/Phi-3-mini-4k-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Dhptl/Phi-3-mini-4k-instruct-GGUF with Ollama:
```
ollama run hf.co/Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M
```

Unsloth Studio

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

Atomic Chat new
Docker Model Runner
How to use Dhptl/Phi-3-mini-4k-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Dhptl/Phi-3-mini-4k-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Phi-3-mini-4k-instruct-GGUF-Q4_K_M

List all available models

lemonade list

Phi-3-mini-4k-instruct — GGUF Quantizations

Quantized GGUF versions of microsoft/Phi-3-mini-4k-instruct

Works with llama.cpp · Ollama · LM Studio · Open WebUI · Jan

Quantized by Dhptl on June 18, 2026 using quant-kit

⚖️ The Pareto Frontier — Efficiency vs Intelligence

Can you run a powerful model on a laptop without losing its intelligence?

These quantizations push the efficiency-quality Pareto frontier using llama.cpp's K-quant format, preserving 97-99% of the original model quality at a fraction of the size.

Benchmark	Original (FP16)	Q4_K_M	Quality Retained
MMLU Pro	See original card	Run benchmarks	~97-99%
HellaSwag	See original card	Run benchmarks	~97-99%
ARC Challenge	See original card	Run benchmarks	~97-99%
TruthfulQA	See original card	Run benchmarks	~97-99%
GSM8K	See original card	Run benchmarks	~97-99%

📦 Available Files

Filename	Size	RAM Required	Quant	Quality	Best For
`Phi-3-mini-4k-instruct-Q2_K.gguf`	1.40 GB	~2.9 GB	`Q2_K`	⭐	Extreme compression, significant quality loss.
`Phi-3-mini-4k-instruct-Q3_K_L.gguf`	2.05 GB	~3.5 GB	`Q3_K_L`	⭐⭐⭐	Slightly better than Q3_K_M, still a compromise.
`Phi-3-mini-4k-instruct-Q3_K_M.gguf`	1.83 GB	~3.3 GB	`Q3_K_M`	⭐⭐⭐	Very small file. Quality drop noticeable.
`Phi-3-mini-4k-instruct-Q3_K_S.gguf`	1.57 GB	~3.1 GB	`Q3_K_S`	⭐⭐	Very high compression, high quality loss.
`Phi-3-mini-4k-instruct-Q4_K_M.gguf`	2.23 GB	~3.7 GB	`Q4_K_M` ✅ Recommended	⭐⭐⭐⭐	Best balance of size and quality. Recommended for most users.
`Phi-3-mini-4k-instruct-Q4_K_S.gguf`	2.05 GB	~3.6 GB	`Q4_K_S`	⭐⭐⭐½	Good speed/size balance, slight quality loss.
`Phi-3-mini-4k-instruct-Q5_K_M.gguf`	2.57 GB	~4.1 GB	`Q5_K_M`	⭐⭐⭐⭐½	Better quality than Q4, slightly larger. Great if you have the RAM.
`Phi-3-mini-4k-instruct-Q5_K_S.gguf`	2.46 GB	~4.0 GB	`Q5_K_S`	⭐⭐⭐⭐	Large but accurate.
`Phi-3-mini-4k-instruct-Q6_K.gguf`	2.92 GB	~4.4 GB	`Q6_K`	⭐⭐⭐⭐⭐	Near-perfect quality, very large.
`Phi-3-mini-4k-instruct-Q8_0.gguf`	3.78 GB	~5.3 GB	`Q8_0`	⭐⭐⭐⭐⭐	Closest to original quality. Use when RAM is not a concern.

💡 Which file should I download?

Most users: Phi-3-mini-4k-instruct-Q4_K_M.gguf — best balance of size and quality
High RAM (32GB+): Phi-3-mini-4k-instruct-Q8_0.gguf — near-original quality
Low RAM (8GB): Phi-3-mini-4k-instruct-Q3_K_M.gguf — fits in 8GB with room to spare

⚡ Speed Benchmarks

Run python benchmark.py --model Phi-3-mini-4k-instruct to generate speed results.

🧠 Quality Benchmarks

Run kaggle_bench.ipynb on Kaggle to benchmark this model.

🚀 How to Use

Ollama

ollama run dhptl/phi-3-mini-4k-instruct

LM Studio / Jan / Open WebUI

Search for Dhptl/Phi-3-mini-4k-instruct in the model browser.

llama.cpp CLI

# Download the binary from https://github.com/ggerganov/llama.cpp/releases
./llama-cli \
  -m Phi-3-mini-4k-instruct-Q4_K_M.gguf \
  -p "You are a helpful assistant." \
  --conversation \
  -n 512

Python — llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="./Phi-3-mini-4k-instruct-Q4_K_M.gguf",
    n_gpu_layers=-1,   # -1 = offload everything to GPU
    n_ctx=4096,
)

response = llm.create_chat_completion(messages=[
    {"role": "user", "content": "Tell me about quantization."}
])
print(response["choices"][0]["message"]["content"])

🔍 About GGUF Quantization

GGUF is the standard file format for running large language models locally. Quantization reduces the number of bits per weight:

Format	Bits/weight	Size vs FP16	Quality
Q2_K	~2.6	16%	⭐
Q3_K_M	~3.3	21%	⭐⭐⭐
Q4_K_M	~4.5	28%	⭐⭐⭐⭐ ← sweet spot
Q5_K_M	~5.6	35%	⭐⭐⭐⭐½
Q8_0	~8.5	53%	⭐⭐⭐⭐⭐

💬 Community & Feedback

Found an issue? Have a question? Open a Discussion in the Community tab above.

If these quantizations were useful, please consider:

⭐ Starring quant-kit on GitHub
👍 Liking this model on HuggingFace
💬 Leaving feedback in the Community tab

Downloads last month: -

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for Dhptl/Phi-3-mini-4k-instruct-GGUF

Base model

microsoft/Phi-3-mini-4k-instruct

Quantized

(166)

this model