Instructions to use unsloth/ERNIE-4.5-21B-A3B-PT-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/ERNIE-4.5-21B-A3B-PT-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/ERNIE-4.5-21B-A3B-PT-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/ERNIE-4.5-21B-A3B-PT-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/ERNIE-4.5-21B-A3B-PT-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 unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/ERNIE-4.5-21B-A3B-PT-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/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/ERNIE-4.5-21B-A3B-PT-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/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/ERNIE-4.5-21B-A3B-PT-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/ERNIE-4.5-21B-A3B-PT-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/ERNIE-4.5-21B-A3B-PT-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/ERNIE-4.5-21B-A3B-PT-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/ERNIE-4.5-21B-A3B-PT-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/ERNIE-4.5-21B-A3B-PT-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/ERNIE-4.5-21B-A3B-PT-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/ERNIE-4.5-21B-A3B-PT-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/ERNIE-4.5-21B-A3B-PT-GGUF with Ollama:
```
ollama run hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL
```
Unsloth Desktop
Docker Model Runner
How to use unsloth/ERNIE-4.5-21B-A3B-PT-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/ERNIE-4.5-21B-A3B-PT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.ERNIE-4.5-21B-A3B-PT-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Atomic Chat

update the gguf

by engrtipusultan - opened Nov 11, 2025

Discussion

engrtipusultan

Nov 11, 2025

Can you please update GGUF.

Model was last updated on 26th sept

https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT/commits/main

shimmyshimmer

Unsloth AI org Nov 14, 2025

Can you please update GGUF.

Model was last updated on 26th sept

https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT/commits/main

We worked with Baidu team actually to implement those fixes which we found. See pinned message

engrtipusultan

Nov 14, 2025

Can you please update GGUF.

Model was last updated on 26th sept

https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT/commits/main

We worked with Baidu team actually to implement those fixes which we found. See pinned message

I cannot see the pinned message. Neither here nor on Bidu HF discussions or commit messages.
I know you guys work with original model providers to provide fixes but are you saying that model updated on 26 sept at baidu HF is same as your GGUFs that are currently here ?

danielhanchen

Unsloth AI org Nov 14, 2025

Can you please update GGUF.

Model was last updated on 26th sept

https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT/commits/main

We worked with Baidu team actually to implement those fixes which we found. See pinned message

I cannot see the pinned message. Neither here nor on Bidu HF discussions or commit messages.
I know you guys work with original model providers to provide fixes but are you saying that model updated on 26 sept at baidu HF is same as your GGUFs that are currently here ?

Yes that is correct, see: https://x.com/ErnieforDevs/status/1976147050463977681

engrtipusultan

Nov 15, 2025

Can you please update GGUF.

Model was last updated on 26th sept

https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT/commits/main

We worked with Baidu team actually to implement those fixes which we found. See pinned message

I cannot see the pinned message. Neither here nor on Bidu HF discussions or commit messages.
I know you guys work with original model providers to provide fixes but are you saying that model updated on 26 sept at baidu HF is same as your GGUFs that are currently here ?

Yes that is correct, see: https://x.com/ErnieforDevs/status/1976147050463977681

As far as I understand that is thinking version. This is non thinking version. GGUFs pointing in that post are to thinking version. This non thinking version was released earlier and updated later.

Please correct me if I am wrong.

engrtipusultan

Jan 25

@danielhanchen
Model is updated. Any changelog for update?

danielhanchen

Unsloth AI org Jan 25

@danielhanchen
Model is updated. Any changelog for update?

Yes it got updated now! Apologies for the previous miscommunication

engrtipusultan

Jan 25

No worries. It is very much appreciated, I just wanted to know what is changed. We enjoy it free of cost, so this is always in my mind.

Thank you to you guys for your wonderful work.

Just on side note. Are you aware of this PR. Will it impact newly shared GGUF.
convert : fix Gemma3N and Ernie4.5Moe
https://github.com/ggml-org/llama.cpp/pull/19084

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