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

Libraries

How to use DuoNeural/Phi-3.5-mini-instruct-LiteRT with LiteRT:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

llama-cpp-python

How to use DuoNeural/Phi-3.5-mini-instruct-LiteRT with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DuoNeural/Phi-3.5-mini-instruct-LiteRT",
	filename="Phi-3.5-mini-instruct-LiteRT_Q4_K_M.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 DuoNeural/Phi-3.5-mini-instruct-LiteRT with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/DuoNeural/Phi-3.5-mini-instruct-LiteRT:Q4_K_M

LM Studio
Jan

vLLM

How to use DuoNeural/Phi-3.5-mini-instruct-LiteRT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DuoNeural/Phi-3.5-mini-instruct-LiteRT:Q4_K_M

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

Unsloth Studio new

How to use DuoNeural/Phi-3.5-mini-instruct-LiteRT 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 DuoNeural/Phi-3.5-mini-instruct-LiteRT 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 DuoNeural/Phi-3.5-mini-instruct-LiteRT to start chatting

Using HuggingFace Spaces for Unsloth

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

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

Lemonade

How to use DuoNeural/Phi-3.5-mini-instruct-LiteRT with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Phi-3.5-mini-instruct-LiteRT

Phi 3.5 Mini Instruct — compact on-device assistant — converted for mobile and edge deployment by DuoNeural.

Source model: microsoft/Phi-3.5-mini-instruct
Format: GGUF Q4_K_M (llama.cpp-compatible)
Parameters: 3.8B
Quantization: 4-bit K-mean (Q4_K_M) — great accuracy/size balance
Target platforms: Android, iOS, desktop edge inference
Converted: 2026-05-06 by Archon / DuoNeural

Why This Model?

Phi-3.5-mini punches way above its weight class — Microsoft's 3.8B model consistently beats models 2-3× larger on reasoning benchmarks. Q4_K_M keeps it under 2.5GB while preserving near-full quality. An ideal edge model when you need real intelligence with a small footprint.

Usage

llama.cpp (CLI)

./llama-cli -m Phi-3.5-mini-instruct-LiteRT_Q4_K_M.gguf \
  -n 512 --temp 0.7 -p "<|system|>You are a helpful assistant.<|end|><|user|>"

Google AI Edge / MediaPipe (Android/iOS)

This GGUF is compatible with MLC-LLM and llama.cpp Android bindings for on-device inference. For use with Google Edge Gallery, convert to .task bundle using MediaPipe LLM conversion tools.

Python via llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="Phi-3.5-mini-instruct-LiteRT_Q4_K_M.gguf",
    n_ctx=4096,
    n_threads=4,
    verbose=False,
)

response = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the derivative of sin(x²)?"},
    ]
)
print(response["choices"][0]["message"]["content"])

Ollama

ollama run hf.co/DuoNeural/Phi-3.5-mini-instruct-LiteRT

Performance Notes

Metric	Value
Quantization	Q4_K_M
RAM required	~3 GB (with context)
Recommended devices	6GB+ RAM phones, laptops
Quantization loss	Minimal — Phi-3.5 is robust to 4-bit quantization

Phi-3.5 Mini Highlights

3.8B params, trained on 3.4T tokens
Strong reasoning, coding, and instruction-following
128K context window (trimmed to device-safe lengths for edge)
One of the top 4B-class models in its generation

About the Conversion

Converted using llama.cpp GGUF pipeline with CUDA acceleration. Source weights downloaded from HuggingFace in safetensors format, converted to F16 GGUF, then quantized to Q4_K_M.

DuoNeural

DuoNeural is an open AI research lab — human + AI in collaboration.

Platform	Link
HuggingFace	huggingface.co/DuoNeural
Website	duoneural.com
GitHub	github.com/DuoNeural
X / Twitter	@DuoNeural
Email	duoneural@proton.me
Newsletter	duoneural.beehiiv.com
Support	buymeacoffee.com/duoneural

DuoNeural Research Publications

Title	DOI
Nano-CTM: Ternary Continuous Thought Machines with Thought-Space Self-Prediction for Efficient Iterative Reasoning	10.5281/zenodo.19775622
Recurrence as World Model: CTM Learns Implicit Belief States in Partially Observable Physical Environments	10.5281/zenodo.19810620
Per-Object Slot Decomposition for Scalable Neural World Modeling: When Does Attention Beat Mean-Field?	10.5281/zenodo.19846804
The Dynamical Horizon Principle: CTM Gates Converge to the Predictability Limit of Dynamical Systems	10.5281/zenodo.19952612

Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura — DuoNeural.

Research Team

Jesse — Vision, hardware, direction
Archon — Lab Director, post-training, abliteration, experiments
Aura — Research AI, literature synthesis, novel proposals

Subscribe to the lab newsletter at duoneural.beehiiv.com for model drops before they go anywhere else.

Downloads last month: 61

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

4-bit

Model tree for DuoNeural/Phi-3.5-mini-instruct-LiteRT

Base model

microsoft/Phi-3.5-mini-instruct

Quantized

(183)

this model