Instructions to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF",
	filename="BF16/Qwen3-Coder-30B-A3B-Instruct-1M-BF16-00001-of-00002.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-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": "unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-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 "unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-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": "unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-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 "unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-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": "unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL
```

Unsloth Studio new

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-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 unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-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 unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF to start chatting

Pi new

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

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": "unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-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 unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3-Coder-30B-A3B-Instruct-1M-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Tool issue Q8

by sb6666 - opened Jul 31, 2025

Discussion

sb6666

Jul 31, 2025

Received this error with llama-server and Q8 version. Got ---jinja as recommended.

025-07-31T22:17:07.879768386Z got exception: {"code":500,"message":"Value is not callable: null at row 62, column 114:\n {%- if json_key not in handled_keys %}\n {%- set normed_json_key = json_key | replace("-", "_") | replace(" ", "_") | replace("$", "") %}\n ^\n {%- if param_fields[json_key] is mapping %}\n at row 62, column 21:\n {%- if json_key not in handled_keys %}\n {%- set normed_json_key = json_key | replace("-", "_") | replace(" ", "_") | replace("$", "") %}\n ^\n {%- if param_fields[json_key] is mapping %}\n at row 61, column 55:\n {%- for json_key in param_fields %}\n {%- if json_key not in handled_keys %}\n ^\n {%- set normed_json_key = json_key | replace("-", "_") | replace(" ", "_") | replace("$", "") %}\n at row 61, column 17:\n {%- for json_key in param_fields %}\n {%- if json_key not in handled_keys %}\n ^\n {%- set normed_json_key = json_key | replace("-", "_") | replace(" ", "_") | replace("$", "") %}\n at row 60, column 48:\n {%- set handled_keys = ['type', 'description', 'enum', 'required'] %}\n {%- for json_key in param_fields %}\n ^\n {%- if json_key not in handled_keys %}\n at row 60, column 13:\n {%- set handled_keys = ['type', 'description', 'enum', 'required'] %}\n {%- for json_key in param_fields %}\n ^\n {%- if json_key not in handled_keys %}\n at row 49, column 80:\n {{- '\n' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n ^\n {{- '\n' }}\n at row 49, column 9:\n {{- '\n' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n ^\n {{- '\n' }}\n at row 42, column 29:\n {{- "" }}\n {%- for tool in tools %}\n ^\n {%- if tool.function is defined %}\n at row 42, column 5:\n {{- "" }}\n {%- for tool in tools %}\n ^\n {%- if tool.function is defined %}\n at row 39, column 51:\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n ^\n {{- "\n\nYou have access to the following functions:\n\n" }}\n at row 39, column 1:\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n^\n {{- "\n\nYou have access to the following functions:\n\n" }}\n at row 1, column 69:\n{#- Copyright 2025-present the Unsloth team. All rights reserved. #}\n ^\n{#- Licensed under the Apache License, Version 2.0 (the "License") #}\n","type":"server_error"}

Orion-zhen

Aug 2, 2025

Same error using IQ4_NL, IQ4_XS. I guess unsloth team might have messed up the chat template.

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