Instructions to use cs2764/DeepSeek-V3.2_dq4-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs2764/DeepSeek-V3.2_dq4-mlx with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

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

model, tokenizer = load("cs2764/DeepSeek-V3.2_dq4-mlx")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Transformers

How to use cs2764/DeepSeek-V3.2_dq4-mlx with Transformers:

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

pipe = pipeline("text-generation", model="cs2764/DeepSeek-V3.2_dq4-mlx")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("cs2764/DeepSeek-V3.2_dq4-mlx", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use cs2764/DeepSeek-V3.2_dq4-mlx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cs2764/DeepSeek-V3.2_dq4-mlx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs2764/DeepSeek-V3.2_dq4-mlx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cs2764/DeepSeek-V3.2_dq4-mlx

SGLang

How to use cs2764/DeepSeek-V3.2_dq4-mlx 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 "cs2764/DeepSeek-V3.2_dq4-mlx" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs2764/DeepSeek-V3.2_dq4-mlx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "cs2764/DeepSeek-V3.2_dq4-mlx" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs2764/DeepSeek-V3.2_dq4-mlx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use cs2764/DeepSeek-V3.2_dq4-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "cs2764/DeepSeek-V3.2_dq4-mlx" --prompt "Once upon a time"

Docker Model Runner
How to use cs2764/DeepSeek-V3.2_dq4-mlx with Docker Model Runner:
```
docker model run hf.co/cs2764/DeepSeek-V3.2_dq4-mlx
```

DeepSeek-V3.2_dq4

This model is a DQ4 quantized version of the original model [DeepSeek-V3.2](Local Model). It was quantized locally using the mlx_lm library.

Quantization Methodology (DQ4)

This model was quantized using the dynamic DQ4 (4-bit / 5-bit / 6-bit / 8-bit mixed) approach, inspired by the methodology described in the mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8 repository.

The weights are mixed based on MLX layers:

Expert layers (switch_mlp / mlp) are quantized to 4-bit.
The first 5 layers are kept at higher quality (6-bit).
Every 5th layer is medium quality (5-bit).
All other layers (e.g. attention, normalization) remain at 8-bit to serve as the "8-bit brain".

Downloads last month: 541

Safetensors

Model size

672B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

4-bit