Instructions to use AmareshHebbar/pocketllm-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AmareshHebbar/pocketllm-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AmareshHebbar/pocketllm-models",
	filename="gemma-3-1b-it-q4_k_m.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 AmareshHebbar/pocketllm-models with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AmareshHebbar/pocketllm-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AmareshHebbar/pocketllm-models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AmareshHebbar/pocketllm-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AmareshHebbar/pocketllm-models: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 AmareshHebbar/pocketllm-models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AmareshHebbar/pocketllm-models: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 AmareshHebbar/pocketllm-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AmareshHebbar/pocketllm-models:Q4_K_M

Use Docker

docker model run hf.co/AmareshHebbar/pocketllm-models:Q4_K_M

LM Studio
Jan

vLLM

How to use AmareshHebbar/pocketllm-models with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AmareshHebbar/pocketllm-models:Q4_K_M

Ollama
How to use AmareshHebbar/pocketllm-models with Ollama:
```
ollama run hf.co/AmareshHebbar/pocketllm-models:Q4_K_M
```

Unsloth Studio

How to use AmareshHebbar/pocketllm-models 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 AmareshHebbar/pocketllm-models 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 AmareshHebbar/pocketllm-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AmareshHebbar/pocketllm-models to start chatting

Atomic Chat new
Docker Model Runner
How to use AmareshHebbar/pocketllm-models with Docker Model Runner:
```
docker model run hf.co/AmareshHebbar/pocketllm-models:Q4_K_M
```

Lemonade

How to use AmareshHebbar/pocketllm-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AmareshHebbar/pocketllm-models:Q4_K_M

Run and chat with the model

lemonade run user.pocketllm-models-Q4_K_M

List all available models

lemonade list

PocketLLM Model Collection

The official model collection for PocketLLM

Private • Offline • On-Device AI for Android

What is PocketLLM?

PocketLLM is an Android app that runs large language models completely on your device — no internet required during inference, no data sent to the cloud, no subscriptions.

This repository hosts the curated model collection optimized for mobile edge inference using:

MediaPipe LLM Inference (for .bin and .task files — Gemma family)
llama.cpp via llama.rn (for .gguf files — Llama, Phi, Qwen, SmolLM, Gemma 3)

Model Catalog

⚡ Ultra Fast — Under 1 GB, fits any Android phone

Model	File	Size	Format	RAM
Qwen 2.5 0.5B	`qwen2.5-0.5b-instruct-q4_k_m.gguf`	0.4 GB	GGUF	2 GB
Gemma 3 1B	`gemma-3-1b-it-q4_k_m.gguf`	0.7 GB	GGUF	2 GB
Llama 3.2 1B	`llama-3.2-1b-instruct-q4_k_m.gguf`	0.8 GB	GGUF	3 GB
SmolLM2 1.7B	`smollm2-1.7b-instruct-q4_k_m.gguf`	1.0 GB	GGUF	3 GB

⚖️ Balanced — 1–2 GB, great quality on mid-range phones

Model	File	Size	Format	RAM
Gemma 1.1 2B (CPU)	`gemma-1.1-2b-it-cpu-int4.bin`	1.35 GB	MediaPipe	4 GB
Gemma 1.1 2B (GPU)	`gemma-1.1-2b-it-gpu-int4.bin`	1.35 GB	MediaPipe	4 GB
Llama 3.2 3B	`llama-3.2-3b-instruct-q4_k_m.gguf`	2.0 GB	GGUF	4 GB

🚀 Powerful — Best quality, needs 5GB+ RAM

Model	File	Size	Format	RAM
Phi-3.5 Mini	`phi-3.5-mini-instruct-q4_k_m.gguf`	2.4 GB	GGUF	5 GB
Gemma 3 4B	`gemma-3-4b-it-q4_k_m.gguf`	2.8 GB	GGUF	6 GB

How to Use in PocketLLM

Models are downloaded directly inside the PocketLLM app. Open the Model Store tab, select a model, and tap Download. The app handles everything automatically.

Direct download URLs:

https://huggingface.co/AmareshHebbar/pocketllm-models/resolve/main/<filename>

Fine-Tuning Roadmap

Coming soon — within the next 2 weeks

We are fine-tuning these base models specifically for on-device conversational AI on mobile:

Goals

Better persona adherence (the model stays in character consistently)
Shorter, more natural responses (base models tend to be verbose on mobile)
Improved memory utilization (uses injected memories naturally)
Better instruction following for small context windows (2048 tokens)
Hindi + English code-switching support (for India market)

Training approach

Base: Llama 3.2 1B, Gemma 3 1B (smallest models first — fastest iteration)
Method: QLoRA fine-tuning (4-bit, similar to the AxioMapper training setup)
Dataset: Curated conversational dataset optimized for mobile edge constraints
Hardware: Single A100 via RunPod
Framework: Unsloth (2x faster fine-tuning, same as AxioMapper)

Fine-tuned models (coming soon)

pocketllm-llama-1b-v1.gguf — Llama 3.2 1B fine-tuned for mobile chat
pocketllm-gemma-1b-v1.gguf — Gemma 3 1B fine-tuned for persona consistency

Model Selection Guide

Your phone has...          Best model to start with
─────────────────────────────────────────────────────
2 GB RAM (budget)    →    Qwen 2.5 0.5B  (fastest)
3 GB RAM             →    Llama 3.2 1B   (balanced speed)
4 GB RAM (mid-range) →    Gemma 1.1 2B   (best all-rounder)
6 GB RAM             →    Llama 3.2 3B   (better quality)
8 GB RAM (flagship)  →    Phi-3.5 Mini   (best for coding)

Technical Details

MediaPipe format (`.bin`, `.task`)

Used for Gemma family
Runs via Google's MediaPipe LLM Inference SDK
Supports CPU and GPU acceleration (Vulkan/OpenCL)
Integrated via react-native-llm-mediapipe

GGUF format (`.gguf`)

Used for Llama, Qwen, Phi, SmolLM, Gemma 3
Runs via llama.cpp (the gold standard for mobile inference)
Q4_K_M quantization — best balance of size and quality
Integrated via llama.rn

Repository Structure

pocketllm-models/
├── gemma-1.1-2b-it-cpu-int4.bin       ← Gemma 2B CPU (MediaPipe)
├── gemma-1.1-2b-it-gpu-int4.bin       ← Gemma 2B GPU (MediaPipe)
├── gemma-3-1b-it-q4_k_m.gguf         ← Gemma 3 1B (GGUF)
├── gemma-3-4b-it-q4_k_m.gguf         ← Gemma 3 4B (GGUF)
├── llama-3.2-1b-instruct-q4_k_m.gguf ← Llama 3.2 1B (GGUF)
├── llama-3.2-3b-instruct-q4_k_m.gguf ← Llama 3.2 3B (GGUF)
├── phi-3.5-mini-instruct-q4_k_m.gguf ← Phi-3.5 Mini (GGUF)
├── qwen2.5-0.5b-instruct-q4_k_m.gguf ← Qwen 2.5 0.5B (GGUF)
└── smollm2-1.7b-instruct-q4_k_m.gguf ← SmolLM2 1.7B (GGUF)

License

Gemma models: Gemma Terms of Use
Llama models: Meta Llama 3.2 Community License
Phi models: MIT License
Qwen models: Apache 2.0
SmolLM2: Apache 2.0
Fine-tuned models by PocketLLM: Apache 2.0

Built By

Amaresh Hebbar

Building PocketLLM: the only mobile app that runs a full AI agent stack — smart routing, persona memory, MCP tools — completely offline on Android.

"Your AI. Your phone. Nobody else's business."

Downloads last month: -

GGUF

Model size

1.0B params

Architecture

gemma3

Hardware compatibility

4-bit