Instructions to use mradermacher/Qwen3-32B-108B-A32B-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Qwen3-32B-108B-A32B-i1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Qwen3-32B-108B-A32B-i1-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Qwen3-32B-108B-A32B-i1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Qwen3-32B-108B-A32B-i1-GGUF",
	filename="Qwen3-32B-108B-A32B.i1-IQ1_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Qwen3-32B-108B-A32B-i1-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 mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_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 mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_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 mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M

Use Docker

docker model run hf.co/mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M

LM Studio
Jan
Ollama
How to use mradermacher/Qwen3-32B-108B-A32B-i1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M
```

Unsloth Studio

How to use mradermacher/Qwen3-32B-108B-A32B-i1-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 mradermacher/Qwen3-32B-108B-A32B-i1-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 mradermacher/Qwen3-32B-108B-A32B-i1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Qwen3-32B-108B-A32B-i1-GGUF to start chatting

How to use mradermacher/Qwen3-32B-108B-A32B-i1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_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": "mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/Qwen3-32B-108B-A32B-i1-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 mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_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 mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use mradermacher/Qwen3-32B-108B-A32B-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M
```

Lemonade

How to use mradermacher/Qwen3-32B-108B-A32B-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Qwen3-32B-108B-A32B-i1-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Qwen3-32B-108B-A32B-i1-GGUF-IQ1_M

List all available models

lemonade list

About

weighted/imatrix quants of https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-108B-A32B

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Qwen3-32B-108B-A32B-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	imatrix	0.1	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	22.6	for the desperate
GGUF	i1-IQ1_M	24.9	mostly desperate
GGUF	i1-IQ2_XXS	28.8
GGUF	i1-IQ2_XS	32.0
GGUF	i1-IQ2_S	32.9
GGUF	i1-IQ2_M	36.0
GGUF	i1-Q2_K_S	37.1	very low quality
GGUF	i1-Q2_K	39.8	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	41.8	lower quality
GGUF	i1-IQ3_XS	44.5
GGUF	i1-Q3_K_S	46.9	IQ3_XS probably better
GGUF	i1-IQ3_S	47.0	beats Q3_K*
GGUF	i1-IQ3_M	47.9
PART 1 PART 2	i1-Q3_K_M	52.1	IQ3_S probably better
PART 1 PART 2	i1-Q3_K_L	56.4	IQ3_M probably better
PART 1 PART 2	i1-IQ4_XS	57.9
PART 1 PART 2	i1-Q4_0	61.5	fast, low quality
PART 1 PART 2	i1-Q4_K_S	61.7	optimal size/speed/quality
PART 1 PART 2	i1-Q4_K_M	65.6	fast, recommended
PART 1 PART 2	i1-Q4_1	67.9
PART 1 PART 2	i1-Q5_K_S	74.6
PART 1 PART 2	i1-Q5_K_M	76.9
PART 1 PART 2	i1-Q6_K	88.9	practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Downloads last month: 1,043

GGUF

Model size

108B params

Architecture

qwen3moe

Hardware compatibility

1-bit

2-bit

3-bit

View +1 variant

Inference Providers NEW

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

Model tree for mradermacher/Qwen3-32B-108B-A32B-i1-GGUF

Base model

LLMcompe-Team-Watanabe/Qwen3-32B-108B-A32B

Quantized

(2)

this model