Instructions to use evalengine/unbound-q-0.8b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use evalengine/unbound-q-0.8b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="evalengine/unbound-q-0.8b-GGUF",
	filename="unbound-q-0.8b-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 evalengine/unbound-q-0.8b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf evalengine/unbound-q-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf evalengine/unbound-q-0.8b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf evalengine/unbound-q-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf evalengine/unbound-q-0.8b-GGUF: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 evalengine/unbound-q-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf evalengine/unbound-q-0.8b-GGUF: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 evalengine/unbound-q-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf evalengine/unbound-q-0.8b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/evalengine/unbound-q-0.8b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use evalengine/unbound-q-0.8b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "evalengine/unbound-q-0.8b-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": "evalengine/unbound-q-0.8b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/evalengine/unbound-q-0.8b-GGUF:Q4_K_M

Ollama
How to use evalengine/unbound-q-0.8b-GGUF with Ollama:
```
ollama run hf.co/evalengine/unbound-q-0.8b-GGUF:Q4_K_M
```

Unsloth Studio

How to use evalengine/unbound-q-0.8b-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 evalengine/unbound-q-0.8b-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 evalengine/unbound-q-0.8b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for evalengine/unbound-q-0.8b-GGUF to start chatting

How to use evalengine/unbound-q-0.8b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf evalengine/unbound-q-0.8b-GGUF:Q4_K_M

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": "evalengine/unbound-q-0.8b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use evalengine/unbound-q-0.8b-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 evalengine/unbound-q-0.8b-GGUF:Q4_K_M

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 evalengine/unbound-q-0.8b-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use evalengine/unbound-q-0.8b-GGUF with Docker Model Runner:
```
docker model run hf.co/evalengine/unbound-q-0.8b-GGUF:Q4_K_M
```

Lemonade

How to use evalengine/unbound-q-0.8b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull evalengine/unbound-q-0.8b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.unbound-q-0.8b-GGUF-Q4_K_M

List all available models

lemonade list

Unbound Q-0.8B GGUF — because there is no boundary

No guarantee — use at your own risk. Reduced safety filtering; can produce harmful or false output. This is the smallest Unbound build — substantially less reliable than E2B/E4B. See the benchmark on the main card.

GGUF quants of evalengine/unbound-q-0.8b for Ollama, llama.cpp, and LM Studio. Built by Chromia & Eval Engine.

Available quants

Single-file GGUFs (no shards — small enough at this size class).

Quant	Size	Notes
Q4_K_M	530 MB	Recommended default — phone-deployable
bf16	1.5 GB	Full precision; reference quality

Run

# llama.cpp
./llama-cli -m unbound-q-0.8b-Q4_K_M.gguf \
  --jinja -ngl 99 \
  --temp 0.7 --top-p 0.8 --top-k 20 --min-p 0.0

Sampling matches Qwen3.5's non-thinking preset (see main card for details). For factual / brand questions drop --temp to ~0.3–0.5.

Headline benchmark

(See main card for the full table — corrected single-judge mimo-v2-pro numbers.)

	refusal	useful_compl.	hallucination	SimpleQA correct	KL vs base
Unbound Q-0.8B	5.00%	6.35%	35.77%	1.50%	0.605

Refusal collapses 91% → 5% (−86 pts); KL ~5× cleaner than the larger Unbound E2B/E4B; useful-compliance and hallucination are materially worse than E2B/E4B — Q-0.8B is not a peer of the larger Unbound builds on quality. It is the on-phone footprint pick: ~530 MB vs 1.5/3.4 GB.

Acknowledgements

Fine-tuned with Unsloth + HF TRL. Abliteration via heretic. Compliance training data distilled from AEON and audited row-by-row; 48 major-fabrication rows decontaminated before this build.

License

Apache-2.0, inherited from Qwen/Qwen3.5-0.8B.

Downloads last month: 338

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

16-bit

Model tree for evalengine/unbound-q-0.8b-GGUF

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

unsloth/Qwen3.5-0.8B

Finetuned

evalengine/unbound-q-0.8b

Quantized

(1)

this model

Collection including evalengine/unbound-q-0.8b-GGUF

Unbound-V1

Collection

The first unbound model built by Eval Engine & Chromia team • 7 items • Updated 2 days ago • 3

evalengine
/

unbound-q-0.8b-GGUF

Unbound Q-0.8B GGUF — because there is no boundary

Available quants

Run

Headline benchmark

Acknowledgements

Links

License

Model tree for evalengine/unbound-q-0.8b-GGUF

Collection including evalengine/unbound-q-0.8b-GGUF

Unbound-V1