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

Libraries

How to use liodon-ai/Qwen3-8B-imatrix-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="liodon-ai/Qwen3-8B-imatrix-GGUF",
	filename="Qwen3-8B-IQ2_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 liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M

Use Docker

docker model run hf.co/liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use liodon-ai/Qwen3-8B-imatrix-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M

Ollama
How to use liodon-ai/Qwen3-8B-imatrix-GGUF with Ollama:
```
ollama run hf.co/liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M
```

Unsloth Studio

How to use liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use liodon-ai/Qwen3-8B-imatrix-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf liodon-ai/Qwen3-8B-imatrix-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": "liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use liodon-ai/Qwen3-8B-imatrix-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf liodon-ai/Qwen3-8B-imatrix-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 "liodon-ai/Qwen3-8B-imatrix-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 liodon-ai/Qwen3-8B-imatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M
```

Lemonade

How to use liodon-ai/Qwen3-8B-imatrix-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

PY-AI-Dev commited on 7 days ago

Commit

ca3ea78

verified ·

1 Parent(s): 656315e

Add iMatrix GGUF quantizations for Qwen3-8B

Browse files

Files changed (9) hide show

.gitattributes +7 -0
Qwen3-8B-IQ2_M.gguf +3 -0
Qwen3-8B-IQ3_M.gguf +3 -0
Qwen3-8B-IQ4_XS.gguf +3 -0
Qwen3-8B-Q4_K_M.gguf +3 -0
Qwen3-8B-Q5_K_M.gguf +3 -0
Qwen3-8B-Q6_K.gguf +3 -0
Qwen3-8B-Q8_0.gguf +3 -0
README.md +65 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3-8B-IQ2_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd93a45dc2c50059776ac1202bb240d887f1205aac1dd2026ebd69381361b4d
+size 3051914848

Qwen3-8B-IQ3_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:75e5bcf77dafcd7a2e3baf015d1f6808caebc98b15a9fd1a9f7fa3978c68869a
+size 3896620640

Qwen3-8B-IQ4_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d434f4c61bc58165b0a5283248df13c507f1a482c04b141dab4b8e3b65169174
+size 4561839712

Qwen3-8B-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:12dad9cbb54c11604f09c56ef951a6155ee2bfc5db361b7edc889ea140e0bd6b
+size 5027784288

Qwen3-8B-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:922ae97f10e542894b594635772652d1dae1f3a8e4eca8c97bd8c2b8bea15a86
+size 5851113056

Qwen3-8B-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:59bdf901577f3bb003ed9b8dc6ca0c3dd9c204ab728e99ca91a824d29c96117f
+size 6725899872

Qwen3-8B-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:08d33608ca3bb9462dfdc1b50d4014cc8cf559ce87afb46e41e9e07af045ca9d
+size 8709518944

README.md ADDED Viewed

	@@ -0,0 +1,65 @@

+---
+license: other
+base_model: Qwen/Qwen3-8B
+pipeline_tag: text-generation
+tags:
+- gguf
+- local-llm
+- llama.cpp
+- lm-studio
+- quantized
+- imatrix
+- sub-4-bit
+- qwen3
+- base_model:Qwen/Qwen3-8B-Base
+---
+# Qwen3-8B — iMatrix GGUF
+GGUF quantizations of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B), published by [Liodon AI](https://huggingface.co/liodon-ai).
+## Quick Start
+**llama.cpp**
+```bash
+llama-cli -hf liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M
+```
+**Ollama**
+```bash
+ollama run hf.co/liodon-ai/Qwen3-8B-imatrix-GGUF:Q4_K_M
+```
+**LM Studio / Jan** — search `liodon-ai/Qwen3-8B-imatrix-GGUF` and pick your quant.
+## Quants
+| Quant | Size | VRAM est. | Notes |
+|-------|------|-----------|-------|
+| `IQ2_M` | 3.05 GB | ~4 GB | 2-bit, iMatrix — smallest usable |
+| `IQ3_M` | 3.90 GB | ~4 GB | 3-bit, iMatrix — great quality/size tradeoff |
+| `IQ4_XS` | 4.56 GB | ~5 GB | 4-bit extra-small, iMatrix |
+| `Q4_K_M` | 5.03 GB | ~6 GB | 4-bit, iMatrix-calibrated (recommended) |
+| `Q5_K_M` | 5.85 GB | ~7 GB | 5-bit, iMatrix-calibrated |
+| `Q6_K` | 6.73 GB | ~8 GB | 6-bit, iMatrix-calibrated, near-lossless |
+| `Q8_0` | 8.71 GB | ~10 GB | 8-bit, essentially lossless |
+## What is iMatrix?
+Standard quantization treats all weights equally. iMatrix runs 128 calibration chunks through
+the full-precision model to find which weights matter most, then allocates more precision where
+it counts. At Q2/Q3/Q4 this means noticeably better coherence and instruction-following —
+**same file size, better output**.
+Calibration: 2M tokens of [WikiText-103](https://huggingface.co/datasets/wikitext).
+> Also see plain (non-iMatrix) quants: `liodon-ai/Qwen3-8B-GGUF`
+## Source
+- **Model**: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
+- **License**: other
+---
+*Quantized by [Liodon AI](https://huggingface.co/liodon-ai)*