Instructions to use modal-labs/GLM-5.3-NVFP4-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modal-labs/GLM-5.3-NVFP4-DFlash with Transformers:

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

pipe = pipeline("text-generation", model="modal-labs/GLM-5.3-NVFP4-DFlash")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("modal-labs/GLM-5.3-NVFP4-DFlash")
model = AutoModel.from_pretrained("modal-labs/GLM-5.3-NVFP4-DFlash", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use modal-labs/GLM-5.3-NVFP4-DFlash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modal-labs/GLM-5.3-NVFP4-DFlash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modal-labs/GLM-5.3-NVFP4-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/modal-labs/GLM-5.3-NVFP4-DFlash

SGLang

How to use modal-labs/GLM-5.3-NVFP4-DFlash 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 "modal-labs/GLM-5.3-NVFP4-DFlash" \
    --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": "modal-labs/GLM-5.3-NVFP4-DFlash",
		"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 "modal-labs/GLM-5.3-NVFP4-DFlash" \
        --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": "modal-labs/GLM-5.3-NVFP4-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use modal-labs/GLM-5.3-NVFP4-DFlash with Docker Model Runner:
```
docker model run hf.co/modal-labs/GLM-5.3-NVFP4-DFlash
```

GLM-5.3-NVFP4-DFlash

Paper | Github | Blog

This repository contains a DFlash draft model for modal-labs/GLM-5.3-NVFP4. It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server.

DFlash uses a lightweight block diffusion draft model to propose multiple tokens in parallel. The target model verifies those proposals, improving serving throughput while preserving the target model's output distribution.

Quick Start

Serve with SGLang v0.5.19 or later:

python -m sglang.launch_server \
  --model-path modal-labs/GLM-5.3-NVFP4 \
  --quantization modelopt_fp4 \
  --tp-size 4 \
  --trust-remote-code \
  --speculative-algorithm DFLASH \
  --speculative-draft-model-path modal-labs/GLM-5.3-NVFP4-DFlash \
  --speculative-dflash-block-size 8 \
  --speculative-draft-model-quantization unquant \
  --speculative-draft-attention-backend fa4 \
  --host 0.0.0.0 \
  --port 30000

Keep the draft model unquantized. Quantizing it lowers the accept length.

License

Distributed under Z.ai's GLM-5.3 License, inherited from the target model.

Citation

If you find DFlash useful, please cite the original paper:

@article{chen2026dflash,
  title   = {{DFlash: Block Diffusion for Flash Speculative Decoding}},
  author  = {Chen, Jian and Liang, Yesheng and Liu, Zhijian},
  journal = {arXiv preprint arXiv:2602.06036},
  year    = {2026}
}