Instructions to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-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 RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

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 RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

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 RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

Use Docker

docker model run hf.co/RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF with Ollama:
```
ollama run hf.co/RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0
```

Unsloth Studio

How to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-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 RDson/Qwen3-30B-A3B-By-Expert-Quantization-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 RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF to start chatting

How to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

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": "RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-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 RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

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 RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

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 "RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0" \
  --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 RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF with Docker Model Runner:
```
docker model run hf.co/RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0
```

Lemonade

How to use RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF:Q8_0

Run and chat with the model

lemonade run user.Qwen3-30B-A3B-By-Expert-Quantization-GGUF-Q8_0

List all available models

lemonade list

Notice: After further investigation into how the layers in tensors are stored, it seems like this is currently not possible. It would require a lot of rewriting the llama.cpp code which would need to be merged etc,. There was a misunderstanding of how I thought it works and how it actually works. Howerver, this is still an interesting topic to potentially explore further in the future, or with another library. I will not be exploring this any further, for now.

=== Keeping this for archival reasons ===

Qwen3-30B-A3B-By-Expert-Quantization-GGUF (BEQ)

This is an experimental implementation of MoE quantization. We use the probability of activating the expert to determine the type of quantization to do for its weights.

Currently, we are using using llama.cpp and there is no implementation of quantizing from hf model to Q4_K_M. Instead, we use Q4_0. This could provide better results. There is currently no support for Q3_0 which could be an interesting combination with Q5_0 for size-to-performance ratio. We use a threshold limit to determine which quantization type to pick.

The implementation can be found on Github.

The activation probabilities for these files is sources from kalomaze/Qwen3-16B-A3B.

Here is a table of some quick perplexity tests I did on the test version of wikitext-2-raw-v1. We used 0.285 threshold. These are short tests just to see if it works.

Simply ran with default as

./build/bin/llama-perplexity -m model_name.gguf -ngl 99 -fa -f wiki.test.raw

Comparison	Value	Size	Extra Info
q81_q4	—	—	—
q8_q51	—	—	—
q8_q5	9.1580 ± 0.07331	21G	—
q8_q41	—	—	—
q8_q4	9.1346 ± 0.07255	—	—
q51_q41	9.4782 ± 0.07698	19G	20059780992
q51_q4	9.2974 ± 0.07461	18.2G	—
q5_q41	—	—	—
q5_q4	9.1854 ± 0.07286	17G	18190432128
q5_q4-q8	9.1900 ± 0.07289	17.6G	17606997888
Qwen3-30B-A3B-UD-Q4_K_XL	9.1906 ± 0.07311	17G	17715663712

Naming format: max-quant_min-quant(q8 here is --outtype, or if left as auto).

Maybe I'll do some more testing if I get the time. But more optimization could show promising results, as this is a jank first implementation.

Downloads last month: 120

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

4-bit

5-bit

8-bit

Inference Providers NEW

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

Model tree for RDson/Qwen3-30B-A3B-By-Expert-Quantization-GGUF

Base model

Qwen/Qwen3-30B-A3B-Base

Finetuned

Qwen/Qwen3-30B-A3B

Quantized

(131)

this model