Instructions to use deepsweet/Qwen3.8-27B-DFlash2-FP16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepsweet/Qwen3.8-27B-DFlash2-FP16 with Transformers:

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

pipe = pipeline("text-generation", model="deepsweet/Qwen3.8-27B-DFlash2-FP16")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("deepsweet/Qwen3.8-27B-DFlash2-FP16")
model = AutoModel.from_pretrained("deepsweet/Qwen3.8-27B-DFlash2-FP16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepsweet/Qwen3.8-27B-DFlash2-FP16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepsweet/Qwen3.8-27B-DFlash2-FP16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepsweet/Qwen3.8-27B-DFlash2-FP16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepsweet/Qwen3.8-27B-DFlash2-FP16

SGLang

How to use deepsweet/Qwen3.8-27B-DFlash2-FP16 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 "deepsweet/Qwen3.8-27B-DFlash2-FP16" \
    --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": "deepsweet/Qwen3.8-27B-DFlash2-FP16",
		"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 "deepsweet/Qwen3.8-27B-DFlash2-FP16" \
        --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": "deepsweet/Qwen3.8-27B-DFlash2-FP16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepsweet/Qwen3.8-27B-DFlash2-FP16 with Docker Model Runner:
```
docker model run hf.co/deepsweet/Qwen3.8-27B-DFlash2-FP16
```

This model was converted to FP16 from z-lab/Qwen3.8-27B-DFlash2 BF16.

What is "DFlash 2"?

DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution.

What is "FP16"?

"FP16" is M1/M2 Apple Silicon only optimization that leads to a very noticeable prompt processing boost. See "Metal FP32 Vs BF16 Vs FP16 benchmark" and jundot/omlx/pull/880 for details.

Use the original model if you have M3+ Apple Silicon.

Downloads last month: 288

Safetensors

Model size

2B params

Tensor type

F16

Model tree for deepsweet/Qwen3.8-27B-DFlash2-FP16

Base model

Qwen/Qwen3.8-27B

Finetuned

z-lab/Qwen3.8-27B-DFlash2

Finetuned

(2)

this model