Instructions to use DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DuoNeural/Qwen2.5-1.5B-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/Qwen2.5-1.5B-Instruct-LiteRT with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT",
	filename="Qwen2.5-1.5B-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/Qwen2.5-1.5B-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/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DuoNeural/Qwen2.5-1.5B-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/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DuoNeural/Qwen2.5-1.5B-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/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DuoNeural/Qwen2.5-1.5B-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/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M

Use Docker

docker model run hf.co/DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M

LM Studio
Jan

vLLM

How to use DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DuoNeural/Qwen2.5-1.5B-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/Qwen2.5-1.5B-Instruct-LiteRT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M

Ollama
How to use DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT with Ollama:
```
ollama run hf.co/DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M
```

Unsloth Studio new

How to use DuoNeural/Qwen2.5-1.5B-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/Qwen2.5-1.5B-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/Qwen2.5-1.5B-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/Qwen2.5-1.5B-Instruct-LiteRT to start chatting

Pi new

How to use DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT with Docker Model Runner:
```
docker model run hf.co/DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M
```

Lemonade

How to use DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-1.5B-Instruct-LiteRT-Q4_K_M

List all available models

lemonade list

Qwen2.5-1.5B-Instruct-LiteRT

Qwen2.5 1.5B Instruct — ultra-compact on-device inference — converted for mobile and edge deployment by DuoNeural.

Source model: Qwen/Qwen2.5-1.5B-Instruct
Format: GGUF Q4_K_M (llama.cpp-compatible, ~986 MB)
Parameters: 1.5B
Quantization: 4-bit K-mean (Q4_K_M) — excellent accuracy/size trade-off for edge devices
Target platforms: Android, iOS, desktop edge inference
Converted: 2026-05-06 by Archon / DuoNeural

Why This Model?

Qwen2.5-1.5B-Instruct is one of the most capable sub-2B instruction-tuned models available. At Q4_K_M the binary is under 1GB, making it viable for on-device deployment on mid-range phones (6GB+ RAM) and all modern laptops.

Usage

llama.cpp (CLI)

./llama-cli -m Qwen2.5-1.5B-Instruct-LiteRT_Q4_K_M.gguf \
  -n 512 --temp 0.7 -p "You are a helpful assistant."

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="Qwen2.5-1.5B-Instruct-LiteRT_Q4_K_M.gguf",
    n_ctx=2048,
    n_threads=4,
    verbose=False,
)

response = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain attention mechanisms in one paragraph."},
    ]
)
print(response["choices"][0]["message"]["content"])

Ollama

ollama run hf.co/DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT

Performance Notes

Metric	Value
File size	~986 MB
RAM required	~1.5 GB (with context)
Recommended devices	4GB+ RAM phones, laptops, SBCs
Quantization loss	Minimal (Q4_K_M is near-lossless for instruction following)

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: 221

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for DuoNeural/Qwen2.5-1.5B-Instruct-LiteRT

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Quantized

(178)

this model