Instructions to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf",
	filename="ggml-model-I1_V.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 XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf
# Run inference directly in the terminal:
llama-cli -hf XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf
# Run inference directly in the terminal:
llama-cli -hf XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

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 XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf
# Run inference directly in the terminal:
./llama-cli -hf XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

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 XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

Use Docker

docker model run hf.co/XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

LM Studio
Jan

vLLM

How to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-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": "XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

Ollama
How to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with Ollama:
```
ollama run hf.co/XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf
```

Unsloth Studio new

How to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-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 XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-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 XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf to start chatting

Pi new

How to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

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": "XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

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 XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

Run Hermes

hermes

Docker Model Runner
How to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with Docker Model Runner:
```
docker model run hf.co/XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf
```

Lemonade

How to use XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-gguf

Run and chat with the model

lemonade run user.Falcon3-1B-Instruct-1.58bit-vlut-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Falcon3-1B-Instruct-1.58bit-vlut-gguf / README.md

XXXXyu

Update README.md

1cf5c2d verified 5 months ago

preview code

raw

history blame contribute delete

3.53 kB

metadata

license: other
license_name: falcon-llm-license
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
base_model: tiiuae/Falcon3-1B-Instruct-1.58bit
tags:
  - text-generation
  - conversational
  - ternary
  - quantized
  - edge-ai
  - on-device
language:
  - en
library_name: vlut.cpp
pipeline_tag: text-generation

Falcon3-1B-Instruct-1.58bit-vlut-gguf

This repository contains state-of-the-art ternary-packed versions of Falcon3-1B-Instruct-1.58bit in GGUF format, optimized for efficient on-device inference using the Vec-LUT method.

Key Features

🎯 SOTA Compression: Achieves BPW (bits per weight) as low as 1.60 through lossless sub-2-bit ternary packing.
⚡ SOTA Performance: Delivers superior throughput (4.2x speedup) in parallel inference scenarios via vector lookup table (LUT).
🔌 Drop-in Ready: Seamless integration with vlut.cpp for immediate deployment on edge devices.

Available Model Variants

Models are named as ggml-model-{PACKING}_{TILE}.gguf:

File Name	Packing (BPW)	Tile Size	Comment
`ggml-model-I1_V.gguf`	`I1_V` (1.60)	1
`ggml-model-I1_V_2.gguf`	`I1_V` (1.60)	2	Recommended
`ggml-model-I2_V.gguf`	`I2_V` (2.00)	1
`ggml-model-I2_V_4.gguf`	`I2_V` (2.00)	4	Recommended
`ggml-model-I2_V_8.gguf`	`I2_V` (2.00)	8

Selection Guide

BPW vs. Speed: I1_V achieves lower memory usage but may not always outperform I2_V in speed.
Tiling Trade-off: Tiled variants (tile size > 1) deliver higher throughput but require larger cache capacity.
Starting Point: Use I1_V_2 or I2_V_4 as a starting point.

For detailed tiling parameter analysis, see Evaluation.md and the paper.

Usage

Prerequisites

Install vlut.cpp (these models require vlut.cpp, not vanilla llama.cpp):

git clone https://github.com/Cipherxzc/vlut.cpp.git
cd vlut.cpp
cmake -B build && cmake --build build --config Release -j4

Download & Run

# Download the recommended variant, e.g., I2_V_4
hf download <repo_id> \
  ggml-model-I2_V_4.gguf --local-dir ./models

# Run parallel inference
./build/bin/llama-batched \
  -m ./models/ggml-model-I2_V_4.gguf \
  -p "I believe the meaning of life is" \
  -np 32 -n 16 -t 1 --temp 0.5 --repeat-penalty 1.5

# Benchmark performance
./build/bin/llama-bench \
  -m ./models/ggml-model-I2_V_4.gguf \
  -t 1 -p 128 -n 0

For comprehensive usage instructions, refer to the vlut.cpp Quick Start Guide.

Citation

If you use these models, please cite our paper:

@article{li2025veclut,
  title={Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices},
  author={Li, Xiangyu and Yin, Chengyu and Wang, Weijun and Wei, Jianyu and Cao, Ting and Liu, Yunxin},
  journal={arXiv preprint arXiv:2512.06443},
  year={2025},
  url={https://arxiv.org/abs/2512.06443}
}

And the original Falcon3 work:

@misc{Falcon3,
    title = {The Falcon 3 family of Open Models},
    author = {TII Team},
    month = {December},
    year = {2024}
}