Instructions to use RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8

SGLang

How to use RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 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 "RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8" \
    --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": "RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8",
		"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 "RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8" \
        --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": "RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8
```

DeepSeek-V4-Flash-NVFP4-FP8

Model Optimizations

This model was obtained by using the following branch with LLM Compressor: https://github.com/vllm-project/llm-compressor/pull/2647

Deployment

This model was deployed using the following branch with vLLM: https://github.com/vllm-project/vllm/pull/41276

vllm serve RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 --tensor-parallel-size 4 --port 8089 --kv_cache_dtype="fp8"

Evaluation

This model has a noticably lower accuracy recovery than the base model due to the base model being released in a quantized format and differences between mxfp4 and nvfp4. More advanced techniques such as GPTQ can be used to increase accuracy recovery beyond this model's current state.

python tests/evals/gsm8k/gsm8k_eval.py

Results:
Accuracy: 0.910
Invalid responses: 0.000
Total latency: 173.006 s
Questions per second: 7.624
Total output tokens: 116217
Output tokens per second: 671.752

python3 tests/evals/mmlu_pro/mmlu_pro_eval.py --port 8089

Results:
Category: all
Accuracy: 0.554
Invalid responses: 0.000
Total latency: 112.065 s
Questions per second: 107.366
Total output tokens: 24076
Output tokens per second: 214.840

For more details on how this model was created and run in LLM Compressor, please contact Kyle Sayers on the vLLM Slack: https://communityinviter.com/apps/vllm-dev/join-vllm-developers-slack

Downloads last month: 4,991

Safetensors

Model size

163B params

Tensor type

I64

F32

BF16

F8_E4M3

Model tree for RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8

Base model

deepseek-ai/DeepSeek-V4-Flash

Quantized

(32)

this model