Instructions to use 6block/Qwen3-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 6block/Qwen3-8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="6block/Qwen3-8B-GGUF",
	filename="Qwen3-8B-IQ3_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 6block/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 6block/Qwen3-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 6block/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 6block/Qwen3-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 6block/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 6block/Qwen3-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 6block/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 6block/Qwen3-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 6block/Qwen3-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/6block/Qwen3-8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use 6block/Qwen3-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "6block/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": "6block/Qwen3-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/6block/Qwen3-8B-GGUF:Q4_K_M

Ollama
How to use 6block/Qwen3-8B-GGUF with Ollama:
```
ollama run hf.co/6block/Qwen3-8B-GGUF:Q4_K_M
```

Unsloth Studio

How to use 6block/Qwen3-8B-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 6block/Qwen3-8B-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 6block/Qwen3-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 6block/Qwen3-8B-GGUF to start chatting

How to use 6block/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 6block/Qwen3-8B-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": "6block/Qwen3-8B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use 6block/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 6block/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 6block/Qwen3-8B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use 6block/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 6block/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 "6block/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"

Docker Model Runner
How to use 6block/Qwen3-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/6block/Qwen3-8B-GGUF:Q4_K_M
```

Lemonade

How to use 6block/Qwen3-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 6block/Qwen3-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-8B-GGUF-Q4_K_M

List all available models

lemonade list

Llamacpp imatrix Quantizations of Qwen3-8B by Qwen

Using llama.cpp at commit 9a3bf2b for quantization.

Original model: https://huggingface.co/Qwen/Qwen3-8B

All quants made using the imatrix option with a bilingual (English + Chinese) and code-heavy calibration dataset, so low-bit quants keep more of their Chinese and coding ability than a English-only calibration would.

Run them in LM Studio, Ollama, or directly with llama.cpp and any llama.cpp based project.

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Description
Qwen3-8B-Q8_0.gguf	Q8_0	8.71GB	Extremely high quality, generally unneeded but max available quant.
Qwen3-8B-Q6_K.gguf	Q6_K	6.73GB	Very high quality, near perfect, recommended.
Qwen3-8B-Q5_K_M.gguf	Q5_K_M	5.85GB	High quality, recommended.
Qwen3-8B-Q4_K_M.gguf	Q4_K_M	5.03GB	Good quality, default size for most use cases, recommended.
Qwen3-8B-IQ4_XS.gguf	IQ4_XS	4.56GB	Decent quality, smaller than Q4_K_S with similar performance, recommended.
Qwen3-8B-IQ3_M.gguf	IQ3_M	3.90GB	Medium-low quality, new method with decent performance comparable to Q3_K_M.
Qwen3-8B-Q2_K.gguf	Q2_K	3.28GB	Very low quality but surprisingly usable.

The .imatrix file used to produce these quants is included in this repo, so anyone can reproduce or extend the quant set with the exact same importance matrix.

Downloading using the hf CLI

Click to view download instructions

First make sure you have the CLI installed:

pip install -U "huggingface_hub[cli]"

Then target the specific file you want (do not clone the whole repo, it is large):

hf download 6block/Qwen3-8B-GGUF --include "Qwen3-8B-Q4_K_M.gguf" --local-dir ./

Which file should I choose?

Click here for details

A great write up with charts showing various performances is provided by Artefact2 here.

The first thing to figure out is how big a model you can run. For that you need to know how much RAM and/or VRAM you have.

If you want the model running as FAST as possible, fit the whole thing in your GPU's VRAM: pick a quant with a file size 1-2GB smaller than your total VRAM.

If you want maximum quality, add your system RAM and your GPU's VRAM together, then pick a quant 1-2GB smaller than that total.

Next, decide between an 'I-quant' and a 'K-quant'.

If you don't want to think about it, grab a K-quant, in the format QX_K_X such as Q5_K_M.

If you want to dig deeper, see the llama.cpp feature matrix.

In short: if you are targeting below Q4 and running cuBLAS (Nvidia) or rocBLAS (AMD), look at the I-quants, in the format IQX_X such as IQ3_M. They are newer and offer better quality for their size. I-quants also work on CPU, but are slower than their K-quant equivalent, so it is a speed-vs-quality tradeoff.

Credits

Quantization pipeline built on llama.cpp by ggml-org.

Thanks to bartowski and kalomaze for establishing the imatrix calibration practice this pipeline follows.

Downloads last month: -

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for 6block/Qwen3-8B-GGUF

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(356)

this model