Instructions to use unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF",
	filename="BF16/Qwen3-Coder-480B-A35B-Instruct-BF16-00001-of-00021.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-480B-A35B-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 unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-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": "unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/Qwen3-Coder-480B-A35B-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 "unsloth/Qwen3-Coder-480B-A35B-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": "unsloth/Qwen3-Coder-480B-A35B-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 "unsloth/Qwen3-Coder-480B-A35B-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": "unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:UD-Q4_K_XL
```

Unsloth Studio new

How to use unsloth/Qwen3-Coder-480B-A35B-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 unsloth/Qwen3-Coder-480B-A35B-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 unsloth/Qwen3-Coder-480B-A35B-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 unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF to start chatting

Pi new

How to use unsloth/Qwen3-Coder-480B-A35B-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 unsloth/Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-Instruct-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Qwen3-Coder-480B-A35B-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 unsloth/Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-Instruct-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3-Coder-480B-A35B-Instruct-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Qwen3-Coder Tool Calling Fixes

#10

pinned

by danielhanchen - opened Jul 31, 2025

Discussion

danielhanchen

Unsloth AI org Jul 31, 2025

•

edited Aug 1, 2025 by

shimmyshimmer

Hey everyone! We managed to fix tool calling via llama.cpp --jinja specifically for serving through llama-server!

PLEASE NOTE: This issue was universal and affected all uploads (not just Unsloth) regardless of source/uploader, and we've communicated with the Qwen team about our fixes!

To get the latest updates, either do:

Download the first file at https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF/tree/main/UD-Q2_K_XL for UD-Q2_K_XL, and replace your current file
Use snapshot_download as usual as in https://docs.unsloth.ai/basics/qwen3-coder-how-to-run-locally#llama.cpp-run-qwen3-tutorial which will auto override the old files
Use the new chat template via --chat-template-file. See GGUF chat template or chat_template.jinja
As an extra, I also made 1 single 150GB UD-IQ1_M file (so Ollama works) at https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF/blob/main/Qwen3-Coder-480B-A35B-Instruct-UD-IQ1_M.gguf

This should solve issues like https://github.com/ggml-org/llama.cpp/issues/14915

danielhanchen pinned discussion Jul 31, 2025

isevendays

Aug 8, 2025

I tried the version and tool calling still crashed.
Here is my command

./build/bin/llama-server \
                         --alias Qwen3-480B-A35B-Instruct \
                         --model /root/models/Qwen3-Coder-480B-A35B-Instruct-GGUF/UD-Q4_K_XL/UD-Q4_K_XL/Qwen3-Coder-480B-A35B-Instruct-UD-Q4_K_XL-00001-of-00006.gguf \
                         --ctx-size 102400 \
                         --cache-type-k q8_0 \
                         --cache-type-v q8_0 \
                         -fa \
                         --temp 0.7 \
                         --top_p 0.8 \
                         --top_k 20 \
                         --n-gpu-layers 99 \
                         --override-tensor "blk\.[0-3]\.ffn_.*=CUDA0,exps=CPU" \
                         --parallel 1 \
                         --threads 104 \
                         --host 0.0.0.0 \
                         --port 8080 \
                         --min_p 0.001 \
                         --threads-batch 52 \
                         --jinja \
                         -b 8192 -ub 4096 \
                         --chat-template-file /root/models/Qwen3-Coder-480B-A35B-Instruct-GGUF/chat_template_working.jinja

I created a chat template that doesn't crash. Feel free to use it https://gist.github.com/iSevenDays/4583750a17ee453783cbaa3acd4ab5fc

florath

Aug 12, 2025

I had a lot of different problems using qwen3-coder with OpenCode, see e.g.: https://github.com/sst/opencode/issues/1809
It just does not follow the rules for tool calling: problems were wrong formatting like array "hidden" in a string instead of a plain array or missing mandatory fields. And this even with the chat template that comes with unsloth/Qwen3-Coder-30B-A3B-Instruct or the template from the last post.
(When using the chat template with vLLM from @isevendays even all tool calls failed for me.)
I experimented with a number of chat templates - without success. (And I'm even not convinced that this is the root cause.)

As a fast and dirty workaround I created a small proxy that can live between the qwen3-coder and the client (e.g. OpenCode) that corrects the tool calls, e.g. adding the mandatory "description" field in the "bash" tool call if not provided by the LLM. https://github.com/florath/qwen3-call-patch-proxy

I'd be happy if somebody could tell me the root cause of these problems and provide a fix. I'd be more than happy to purge my hackisch workaround if not needed any longer.

tifoji

Sep 1, 2025

I adapted the earlier posted version to get it to work in opencode https://gist.github.com/tifoji/8559819fa289f1fe26fa5fd86d62216f

llama-server \
    --model "Qwen3-Coder-480B-A35B-Instruct-UD-Q4_K_XL-00001-of-00006.gguf" \
    --alias qwen3-coder \
    --threads -1 \
    --n-gpu-layers 99 \
    -ot ".ffn_.*_exps.=CPU" \
    --temp 0.7 \
    --min-p 0.0 \
    --top-p 0.8 \
    --top-k 20 \
    --repeat-penalty 1.05 \
    --jinja \
    --reasoning-format auto \
    --no-context-shift \
    --ctx-size 131072 \
    --chat-template-file chat_template_llamacpp.jinja

First prompt "explain daylight savings time" took a long time to respond.

prompt eval time =  249554.33 ms /  9433 tokens (   26.46 ms per token,    37.80 tokens per second)
       eval time =   54438.50 ms /   224 tokens (  243.03 ms per token,     4.11 tokens per second)
      total time =  303992.83 ms /  9657 tokens
srv  update_slots: all slots are idle

Subsequent ones were faster , for example "what is the current temperature in san francisco" ... It tried a webfetch first but failed and made a bash curl tool call successfully

slot print_timing: id  0 | task 584 | 
prompt eval time =    1926.32 ms /    30 tokens (   64.21 ms per token,    15.57 tokens per second)
       eval time =   18938.54 ms /    81 tokens (  233.81 ms per token,     4.28 tokens per second)
      total time =   20864.86 ms /   111 tokens

Tested on mac studio 512GB

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