Instructions to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF",
	filename="Qwen3-Coder-30B-A3B-Instruct-IQ3_S-2.66bpw.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 byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S
# Run inference directly in the terminal:
llama-cli -hf byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S
# Run inference directly in the terminal:
llama-cli -hf byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

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 byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S
# Run inference directly in the terminal:
./llama-cli -hf byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

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 byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

Use Docker

docker model run hf.co/byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

LM Studio
Jan

vLLM

How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "byteshape/Qwen3-Coder-30B-A3B-Instruct-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": "byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

SGLang

How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with Ollama:
```
ollama run hf.co/byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S
```

Unsloth Studio

How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-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 byteshape/Qwen3-Coder-30B-A3B-Instruct-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 byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

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": "byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

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 byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

Run Hermes

hermes

Docker Model Runner
How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S
```

Lemonade

How to use byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF:IQ3_S

Run and chat with the model

lemonade run user.Qwen3-Coder-30B-A3B-Instruct-GGUF-IQ3_S

List all available models

lemonade list

Best for 5060ti 16GB?

by nikhilprasanth - opened Feb 18

Discussion

nikhilprasanth

Feb 18

Hi,
I Have 64gb ddr5 and 5060ti 16GB GPU, which quant is best for the hardware? And does these quants have impact on agentic workflows in cline or open code compared to bf16 baseline?

Ali93H

ByteShape org Feb 18

•

edited Feb 18

I haven’t tested it on an RTX 5060 Ti yet, but I would expect behavior similar to the RTX 4080.

In that case, I would recommend:

Qwen3-Coder-30B-A3B-Instruct – IQ3_S (3.12 bpw)
https://huggingface.co/byteshape/Qwen3-Coder-30B-A3B-Instruct-GGUF/blob/main/Qwen3-Coder-30B-A3B-Instruct-IQ3_S-3.12bpw.gguf

This configuration should leave roughly 4 GB of VRAM available for context, which should comfortably support at least a 32K context window.

You can find the full performance plots here:
https://byteshape.com/blogs/Devstral-Small-2-24B-Instruct-2512/

In terms of agentic workflows , these quants should perform well. We’ve evaluated them across several coding and tool-calling benchmarks, and they remain solid relative to the BF16 baseline.

Let us know how your setup goes.

nikhilprasanth

Feb 19

I tried the same with 32k context- really good performance! initially I'm getting 130+ tok/s. It is using tools well too!

nikhilprasanth

Feb 19

The optimization is really crazy, for the same parameters, im getting 135 tps with this vs 30 for Qwen3-Coder-30B-A3B-Instruct-UD-IQ3_XXS

Ali93H

ByteShape org Feb 19

Many thanks for the update!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment