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

Libraries

How to use ooousay/bitnet-ios-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ooousay/bitnet-ios-models",
	filename="Falcon3-1B-Instruct-i2s.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ooousay/bitnet-ios-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ooousay/bitnet-ios-models
# Run inference directly in the terminal:
llama-cli -hf ooousay/bitnet-ios-models

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ooousay/bitnet-ios-models
# Run inference directly in the terminal:
llama-cli -hf ooousay/bitnet-ios-models

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 ooousay/bitnet-ios-models
# Run inference directly in the terminal:
./llama-cli -hf ooousay/bitnet-ios-models

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 ooousay/bitnet-ios-models
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ooousay/bitnet-ios-models

Use Docker

docker model run hf.co/ooousay/bitnet-ios-models

LM Studio
Jan
Ollama
How to use ooousay/bitnet-ios-models with Ollama:
```
ollama run hf.co/ooousay/bitnet-ios-models
```

Unsloth Studio new

How to use ooousay/bitnet-ios-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 ooousay/bitnet-ios-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 ooousay/bitnet-ios-models to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use ooousay/bitnet-ios-models with Docker Model Runner:
```
docker model run hf.co/ooousay/bitnet-ios-models
```

Lemonade

How to use ooousay/bitnet-ios-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ooousay/bitnet-ios-models

Run and chat with the model

lemonade run user.bitnet-ios-models-{{QUANT_TAG}}

List all available models

lemonade list

bitnet-ios-models / README.md

denis

Upload README.md with huggingface_hub

26fdb70 verified 3 months ago

preview code

raw

history blame contribute delete

2.33 kB

	---
	license: mit
	tags:
	- bitnet
	- 1-bit
	- gguf
	- ios
	- apple-silicon
	- arm64-neon
	---

	# BitNet iOS Models

	Pre-converted GGUF models for use with [BitNet-iOS](https://github.com/dgavriloff/BitNet-iOS) — native 1-bit LLM inference on Apple Silicon using ARM64 NEON TL1 kernels.

	These GGUFs were quantized using the BitNet.cpp `i2_s` format with locally-built `llama-quantize` from the [microsoft/BitNet](https://github.com/microsoft/BitNet) repo. Using GGUFs from other sources may produce incorrect output due to differences in `i2_s` packing between llama-quantize versions.

	## Models

	\| File \| Original Model \| Type \| Size \| License \|
	\|------\|---------------\|------\|------\|---------\|
	\| `Falcon3-1B-Instruct-i2s.gguf` \| [tiiuae/Falcon3-1B-Instruct-1.58bit](https://huggingface.co/tiiuae/Falcon3-1B-Instruct-1.58bit) \| Instruct (chat) \| 1.36 GB \| [TII Falcon License 2.0](https://falconllm.tii.ae/falcon-terms-and-conditions.html) \|
	\| `bitnet-b1.58-large-i2s.gguf` \| [microsoft/bitnet_b1_58-large](https://huggingface.co/1bitLLM/bitnet_b1_58-large) \| Base (completion) \| 270 MB \| MIT \|

	## Usage

	These models are designed for the BitNet-iOS demo app, which downloads them automatically from this repo. They can also be used with the BitNet-iOS CLI:

	```bash
	# Instruct model (chat)
	.build/debug/BitNetCLI /path/to/Falcon3-1B-Instruct-i2s.gguf --chat

	# Base model (completion)
	.build/debug/BitNetCLI /path/to/bitnet-b1.58-large-i2s.gguf "Once upon a time"
	```

	## Why self-hosted GGUFs?

	The BitNet TL1 kernels are sensitive to the exact `i2_s` quantization format. GGUFs from the original model repos (e.g., tiiuae's Falcon3 GGUF) were quantized with a different version of `llama-quantize` and differ by ~224 bytes in header metadata. This causes the ARM64 NEON kernels to silently produce garbage output. These GGUFs were converted with the same toolchain used to build the BitNet-iOS XCFramework, ensuring compatibility.

	## Attribution

	- Falcon3-1B-Instruct by [Technology Innovation Institute (TII)](https://www.tii.ae/) — [TII Falcon License 2.0](https://falconllm.tii.ae/falcon-terms-and-conditions.html)
	- BitNet b1.58 Large by [Microsoft Research](https://github.com/microsoft/BitNet) — MIT License
	- Quantization via [microsoft/BitNet](https://github.com/microsoft/BitNet) (MIT License)