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

Libraries

How to use Quipuai/quipu-0.8b-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Quipuai/quipu-0.8b-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Quipuai/quipu-0.8b-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 Quipuai/quipu-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Quipuai/quipu-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 serve -hf Quipuai/quipu-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Quipuai/quipu-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 Quipuai/quipu-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Quipuai/quipu-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 Quipuai/quipu-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Quipuai/quipu-0.8b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Quipuai/quipu-0.8b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Quipuai/quipu-0.8b-GGUF with Ollama:
```
ollama run hf.co/Quipuai/quipu-0.8b-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Quipuai/quipu-0.8b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Quipuai/quipu-0.8b-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Quipuai/quipu-0.8b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use Quipuai/quipu-0.8b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Quipuai/quipu-0.8b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.quipu-0.8b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Quipuai/quipu-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 serve -hf Quipuai/quipu-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 Quipuai/quipu-0.8b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Quipuai/quipu-0.8b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Quipuai/quipu-0.8b-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Quipuai/quipu-0.8b-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Quipu 0.8B — GGUF

GGUF quantized versions of Quipuai/quipu-0.8b, ready to run with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes.

Quipu 0.8B is a LoRA fine-tune of Qwen3.5-0.8B, tuned for step-by-step reasoning, honest tool-calling behavior, consistent identity, and lightweight coding help.

Available quantizations

Quant	Size	Notes
Q2_K	422 MB	Smallest, noticeable quality loss
Q3_K_S / Q3_K_M / Q3_K_L	435–491 MB	Small, usable for simple tasks
Q4_0 / Q4_1	501–533 MB	Legacy 4-bit, works everywhere
Q4_K_S / Q4_K_M	505–529 MB	Recommended default — best size/quality balance
Q5_0 / Q5_1	564–595 MB	Better quality, still compact
Q5_K_S / Q5_K_M	564–578 MB	Good quality, low loss
Q6_K	—	Near-lossless
Q8_0	—	Best quality, closest to full precision
F16	—	Full precision, reference version

At 0.8B parameters the model is already tiny, so Q4_K_M or Q8_0 are the sweet spots — Q4_K_M if you want the smallest footprint with minimal loss, Q8_0 if you want the closest to full quality and don't mind a slightly bigger file.

Running with Ollama

ollama run hf.co/Quipuai/quipu-0.8b-GGUF:Q4_K_M

Swap Q4_K_M for any quant tag from the table above.

Running with llama.cpp

./llama-cli -m quipu-0.8b-Q4_K_M.gguf -p "Who are you?"

Full precision / training

For the unquantized safetensors model (for fine-tuning or merging), see Quipuai/quipu-0.8b.

Downloads last month: 198

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Quipuai/quipu-0.8b-GGUF

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Adapter

Quipuai/quipu-0.8b

Adapter

(2)

this model