Instructions to use rileyseaburg/distillix-100m-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rileyseaburg/distillix-100m-v0.3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rileyseaburg/distillix-100m-v0.3")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rileyseaburg/distillix-100m-v0.3", dtype="auto")

llama-cpp-python

How to use rileyseaburg/distillix-100m-v0.3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rileyseaburg/distillix-100m-v0.3",
	filename="distillix-v0.3.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 rileyseaburg/distillix-100m-v0.3 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rileyseaburg/distillix-100m-v0.3
# Run inference directly in the terminal:
llama-cli -hf rileyseaburg/distillix-100m-v0.3

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rileyseaburg/distillix-100m-v0.3
# Run inference directly in the terminal:
llama-cli -hf rileyseaburg/distillix-100m-v0.3

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 rileyseaburg/distillix-100m-v0.3
# Run inference directly in the terminal:
./llama-cli -hf rileyseaburg/distillix-100m-v0.3

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 rileyseaburg/distillix-100m-v0.3
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rileyseaburg/distillix-100m-v0.3

Use Docker

docker model run hf.co/rileyseaburg/distillix-100m-v0.3

LM Studio
Jan

vLLM

How to use rileyseaburg/distillix-100m-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rileyseaburg/distillix-100m-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rileyseaburg/distillix-100m-v0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rileyseaburg/distillix-100m-v0.3

SGLang

How to use rileyseaburg/distillix-100m-v0.3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rileyseaburg/distillix-100m-v0.3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rileyseaburg/distillix-100m-v0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rileyseaburg/distillix-100m-v0.3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rileyseaburg/distillix-100m-v0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use rileyseaburg/distillix-100m-v0.3 with Ollama:
```
ollama run hf.co/rileyseaburg/distillix-100m-v0.3
```

Unsloth Studio new

How to use rileyseaburg/distillix-100m-v0.3 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 rileyseaburg/distillix-100m-v0.3 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 rileyseaburg/distillix-100m-v0.3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rileyseaburg/distillix-100m-v0.3 to start chatting

Docker Model Runner
How to use rileyseaburg/distillix-100m-v0.3 with Docker Model Runner:
```
docker model run hf.co/rileyseaburg/distillix-100m-v0.3
```

Lemonade

How to use rileyseaburg/distillix-100m-v0.3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rileyseaburg/distillix-100m-v0.3

Run and chat with the model

lemonade run user.distillix-100m-v0.3-{{QUANT_TAG}}

List all available models

lemonade list

Distillix 100M v0.3

A 100M parameter BitNet b1.58 language model trained via knowledge distillation.

Model Details

Architecture: Frankenstein LLM combining best practices
- BitNet b1.58 (Microsoft) - 1.58-bit ternary weights
- Llama-2 tokenizer (32k vocab)
- Llama 3 GQA (12Q/4KV heads for 3x KV cache reduction)
- Gemma 2/3 stability (QK-Norm + Logit Soft-Capping)
- Extended RoPE (theta=1M for long context)
Parameters: ~100M
Training: 500 steps on 765 samples (initial training)
Optimizer: Stanford Muon + AdamW hybrid

Architecture Specs

Component	Value
Hidden dim	768
Layers	12
Q Heads	12
KV Heads	4 (GQA)
Head dim	64
MLP dim	2048
Vocab size	32,000
Max seq len	2,048
RoPE theta	1,000,000

Training

Trained with the Muon optimizer from Stanford, which showed characteristic "Muon Drop" - steep loss reduction:

Initial loss: 10.59
Final loss: 1.04 (90% reduction in 6 minutes)
Hardware: RTX 2080 Super (8GB VRAM)

Files

distillix-v0.safetensors - SafeTensors format (382 MB)
distillix-v0.3.gguf - GGUF format for llama.cpp (191 MB)
model_500steps.pt - PyTorch checkpoint

Usage

import torch
from safetensors.torch import load_file

# Load model weights
state_dict = load_file("distillix-v0.safetensors")

# For inference, use with llama.cpp or bitnet.cpp
# GGUF file is provided for CPU inference

Limitations

Early training (500 steps) - model needs more training
Limited training data (765 samples)
Best used as a starting point for further fine-tuning

License

Apache 2.0

Citation

@misc{distillix2025,
  title={Distillix: Frankenstein BitNet b1.58 Knowledge Distillation},
  author={Seaburg, Riley},
  year={2025},
  url={https://github.com/rileyseaburg/distillix}
}

Downloads last month: 27

GGUF

Model size

0.1B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

rileyseaburg
/

distillix-100m-v0.3