Instructions to use mlx-community/LLaDA-8B-Instruct-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/LLaDA-8B-Instruct-mlx-4bit with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/LLaDA-8B-Instruct-mlx-4bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mlx-community/LLaDA-8B-Instruct-mlx-4bit", trust_remote_code=True, dtype="auto")

MLX

How to use mlx-community/LLaDA-8B-Instruct-mlx-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/LLaDA-8B-Instruct-mlx-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use mlx-community/LLaDA-8B-Instruct-mlx-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/LLaDA-8B-Instruct-mlx-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/LLaDA-8B-Instruct-mlx-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlx-community/LLaDA-8B-Instruct-mlx-4bit

SGLang

How to use mlx-community/LLaDA-8B-Instruct-mlx-4bit 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 "mlx-community/LLaDA-8B-Instruct-mlx-4bit" \
    --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": "mlx-community/LLaDA-8B-Instruct-mlx-4bit",
		"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 "mlx-community/LLaDA-8B-Instruct-mlx-4bit" \
        --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": "mlx-community/LLaDA-8B-Instruct-mlx-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

MLX LM

How to use mlx-community/LLaDA-8B-Instruct-mlx-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/LLaDA-8B-Instruct-mlx-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/LLaDA-8B-Instruct-mlx-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/LLaDA-8B-Instruct-mlx-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use mlx-community/LLaDA-8B-Instruct-mlx-4bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/LLaDA-8B-Instruct-mlx-4bit
```

`ValueError: Model type llada not supported.`, anyone knows what I need to do?

by very-cooluser - opened Mar 23, 2025

Discussion

very-cooluser

Mar 23, 2025

•

edited Mar 23, 2025

The whole message is below, anyone knows if I'm missing something?

  File "./lib/python3.11/site-packages/mlx_lm/utils.py", line 148, in _get_classes
    arch = importlib.import_module(f"mlx_lm.models.{model_type}")
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.11/importlib/__init__.py", line 126, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "<frozen importlib._bootstrap>", line 1206, in _gcd_import
  File "<frozen importlib._bootstrap>", line 1178, in _find_and_load
  File "<frozen importlib._bootstrap>", line 1142, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'mlx_lm.models.llada'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "./inf.py", line 3, in <module>
    model, tokenizer = load("mlx-community/LLaDA-8B-Instruct-mlx-4bit")
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "./lib/python3.11/site-packages/mlx_lm/utils.py", line 785, in load
    model, config = load_model(model_path, lazy)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "./lib/python3.11/site-packages/mlx_lm/utils.py", line 720, in load_model
    model_class, model_args_class = get_model_classes(config=config)
                                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "./lib/python3.11/site-packages/mlx_lm/utils.py", line 152, in _get_classes
    raise ValueError(msg)
ValueError: Model type llada not supported.

arudedogg

MLX Community org May 24, 2025

Same here on M4 Mac Mini, with both the 4bit and 8bit variants.

🥲 Failed to load the model

Failed to load model

Error when loading model: ValueError: Model type llada not supported.

jatin-exe

Jun 22, 2025

do we have a fix for this ? Im using mlx-lm==0.25.2, description says it should work with 0.21.0

desmond108

Jul 6, 2025

Got the same error too on M1 Mac Mini with 4 bit variant:

🥲 Failed to load the model

Failed to load model

Error when loading model: ValueError: Model type llada not supported.

desmond108

Jul 6, 2025

Was just told on the thread for the 4-bit DiffuCoder that I have to wait for new LM Studio 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