Instructions to use jimdilkes/cair-qwen3-8b-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 jimdilkes/cair-qwen3-8b-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 jimdilkes/cair-qwen3-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jimdilkes/cair-qwen3-8b-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 jimdilkes/cair-qwen3-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jimdilkes/cair-qwen3-8b-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 jimdilkes/cair-qwen3-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jimdilkes/cair-qwen3-8b-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 jimdilkes/cair-qwen3-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jimdilkes/cair-qwen3-8b-gguf:Q4_K_M

Use Docker

docker model run hf.co/jimdilkes/cair-qwen3-8b-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use jimdilkes/cair-qwen3-8b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jimdilkes/cair-qwen3-8b-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": "jimdilkes/cair-qwen3-8b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jimdilkes/cair-qwen3-8b-gguf:Q4_K_M

Ollama
How to use jimdilkes/cair-qwen3-8b-gguf with Ollama:
```
ollama run hf.co/jimdilkes/cair-qwen3-8b-gguf:Q4_K_M
```
Unsloth Desktop

How to use jimdilkes/cair-qwen3-8b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jimdilkes/cair-qwen3-8b-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": "jimdilkes/cair-qwen3-8b-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jimdilkes/cair-qwen3-8b-gguf with Docker Model Runner:
```
docker model run hf.co/jimdilkes/cair-qwen3-8b-gguf:Q4_K_M
```

Lemonade

How to use jimdilkes/cair-qwen3-8b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jimdilkes/cair-qwen3-8b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.cair-qwen3-8b-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use jimdilkes/cair-qwen3-8b-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 jimdilkes/cair-qwen3-8b-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 jimdilkes/cair-qwen3-8b-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jimdilkes/cair-qwen3-8b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jimdilkes/cair-qwen3-8b-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 "jimdilkes/cair-qwen3-8b-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"

CAIR Qwen3-8B (Q4_K_M GGUF)

LoRA SFT of Qwen/Qwen3-8B on the Home-Assistant-Requests V1 dataset, merged into the base weights and quantized to GGUF Q4_K_M.

Note: this checkpoint was trained on the V1 dataset (ShareGPT format, single-turn, no tool calling). A V2 model trained on jimdilkes/cair-v2-canonical (tool calling, multilingual, recovery-pattern supervision) is in progress.

Training config


Base model	`Qwen/Qwen3-8B`
Dataset	`acon96/Home-Assistant-Requests` (V1, ShareGPT, no tool calls)
Method	LoRA SFT (TRL `SFTTrainer`)
Epochs	3
Per-device batch size	16
Gradient accumulation	1
Learning rate	2e-4 (cosine, warmup ratio 0.03)
Max sequence length	2048
Precision	bf16
LoRA rank / alpha / dropout	16 / 32 / 0.05
LoRA target modules	`all-linear`
Loss	completion-only
Seed	1
Hardware	2× H100 / A100 (torchrun)

Quantization

LoRA adapter merged into the base model in bf16, then converted to GGUF and quantized to Q4_K_M via llama.cpp (convert_hf_to_gguf.py + llama-quantize).


Format	GGUF
Quantization	Q4_K_M
File size	4.7 GB

Usage

llama.cpp

llama-cli -m cair-qwen3-8b-Q4_K_M.gguf \
    -p "You are 'Al', a helpful AI Assistant that controls the devices in a house."

Ollama

ollama create cair-qwen3-8b -f Modelfile

Source

Training pipeline + GGUF conversion scripts: https://github.com/jim-dilkes/CAIR-finetune

Downloads last month: 7

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for jimdilkes/cair-qwen3-8b-gguf

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Adapter

(2149)

this model

Dataset used to train jimdilkes/cair-qwen3-8b-gguf

Collection including jimdilkes/cair-qwen3-8b-gguf

CAIR-finetune-v1

Collection

3 items • Updated Jun 4