Instructions to use VertexResearch/Vertex-0.6-15M-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use VertexResearch/Vertex-0.6-15M-Instruct-GGUF 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 VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16

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 VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16

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 VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16

Use Docker

docker model run hf.co/VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16

LM Studio
Jan

vLLM

How to use VertexResearch/Vertex-0.6-15M-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VertexResearch/Vertex-0.6-15M-Instruct-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": "VertexResearch/Vertex-0.6-15M-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16

Ollama
How to use VertexResearch/Vertex-0.6-15M-Instruct-GGUF with Ollama:
```
ollama run hf.co/VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16
```
Unsloth Desktop
Docker Model Runner
How to use VertexResearch/Vertex-0.6-15M-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16
```

Lemonade

How to use VertexResearch/Vertex-0.6-15M-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VertexResearch/Vertex-0.6-15M-Instruct-GGUF:F16

Run and chat with the model

lemonade run user.Vertex-0.6-15M-Instruct-GGUF-F16

List all available models

lemonade list

Atomic Chat

Vertex 0.6 15M Instruct — GGUF

A tiny (~15M-param) chat model from the Vertex 0.6 family. Qwen3 architecture (hidden 256, 10 layers, GQA, 20000 vocab, ctx 2048), pretrained from scratch on 12B tokens of Ultra-FineWeb and Ultra-FineWeb-L3 English (natural + synthetic-rewrite mix), then taken through a custom post-training pipeline for chat.

What it does: coherent multi-turn chat with in-context memory (recalls your name/details from 1000+ tokens back, and says so honestly when you haven't told it).

What it doesn't do: facts, reasoning, math, code. At this size, knowledge is decorative — treat outputs as conversation, not information.

Usage

ChatML template (embedded). Sampling strongly recommended — greedy decoding loops badly at this size:

temperature 0.6, top_p 0.9, repeat_penalty 1.3

GGUF builds: Vertex-0.6-15M-Instruct-GGUF.

Trained end-to-end on a single RTX 4060 Laptop (8GB).

Training data

Fine-tuned from Vertex-0.6-15M-Base (pretrained on openbmb/Ultra-FineWeb + openbmb/Ultra-FineWeb-L3, 12B tokens). Instruction tuning was done with a custom post-training pipeline.