Instructions to use KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit with Transformers:

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

pipe = pipeline("text-generation", model="KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit", trust_remote_code=True, dtype="auto")

MLX

How to use KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit 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("KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit")

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 KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit

SGLang

How to use KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit 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 "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit" \
    --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": "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit",
		"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 "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit" \
        --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": "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

MLX LM

How to use KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit with Docker Model Runner:
```
docker model run hf.co/KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit
```

KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit

The Model KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit was converted to MLX format from LGAI-EXAONE/EXAONE-Deep-32B using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

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

Downloads last month: 8

Safetensors

Model size

4B params

Tensor type

F16

U32

MLX

Hardware compatibility

3-bit

Model tree for KYUNGYONG/EXAONE-Deep-32B-mlx-3Bit

Base model

LGAI-EXAONE/EXAONE-3.5-32B-Instruct

Finetuned

LGAI-EXAONE/EXAONE-Deep-32B

Finetuned

(15)

this model