Instructions to use deepsweet/Qwen3.6-27B-DFlash-FP16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepsweet/Qwen3.6-27B-DFlash-FP16 with Transformers:

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

pipe = pipeline("text-generation", model="deepsweet/Qwen3.6-27B-DFlash-FP16", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("deepsweet/Qwen3.6-27B-DFlash-FP16", trust_remote_code=True)
model = AutoModel.from_pretrained("deepsweet/Qwen3.6-27B-DFlash-FP16", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepsweet/Qwen3.6-27B-DFlash-FP16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepsweet/Qwen3.6-27B-DFlash-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/Qwen3.6-27B-DFlash-FP16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepsweet/Qwen3.6-27B-DFlash-FP16

SGLang

How to use deepsweet/Qwen3.6-27B-DFlash-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/Qwen3.6-27B-DFlash-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/Qwen3.6-27B-DFlash-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/Qwen3.6-27B-DFlash-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/Qwen3.6-27B-DFlash-FP16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepsweet/Qwen3.6-27B-DFlash-FP16 with Docker Model Runner:
```
docker model run hf.co/deepsweet/Qwen3.6-27B-DFlash-FP16
```

deepsweet commited on 12 days ago

Commit

3d5d72d

verified ·

1 Parent(s): 3122315

Add files using upload-large-folder tool

Browse files

Files changed (3) hide show

README.md +22 -0
config.json +53 -0
model.safetensors +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,22 @@

+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+  - dflash
+  - speculative-decoding
+  - draft-model
+base_model: z-lab/Qwen3.6-27B-DFlash
+---
+This model was [converted](https://github.com/deepsweet/bf16-to-fp16) to FP16 from [z-lab/Qwen3.6-27B-DFlash](https://huggingface.co/z-lab/Qwen3.6-27B-DFlash) BF16.
+## What is "DFlash"?
+>DFlash is a novel speculative decoding method that utilizes a lightweight block diffusion model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed.
+## What is "FP16"?
+"FP16" is M1/M2 Apple Silicon only optimization that leads to a very noticeable prompt processing boost. See [jundot/omlx/issues/604](https://github.com/jundot/omlx/issues/604) and [jundot/omlx/pull/880](https://github.com/jundot/omlx/pull/880) for details.
+Use the original model if you have M3+ Apple Silicon.

config.json ADDED Viewed

	@@ -0,0 +1,53 @@

+{
+  "architectures": [
+    "DFlashDraftModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModel": "dflash.DFlashDraftModel"
+  },
+  "block_size": 16,
+  "bos_token_id": null,
+  "dflash_config": {
+    "mask_token_id": 248070,
+    "target_layer_ids": [
+      1,
+      16,
+      31,
+      46,
+      61
+    ]
+  },
+  "dtype": "float16",
+  "eos_token_id": 248044,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 5,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 5,
+  "num_key_value_heads": 8,
+  "num_target_layers": 64,
+  "pad_token_id": 248044,
+  "rms_norm_eps": 1e-06,
+  "sliding_window": 2048,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.3",
+  "use_cache": true,
+  "use_sliding_window": true,
+  "vocab_size": 248320,
+  "rope_theta": 10000000,
+  "rope_scaling": null
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6a287575d124c04f05ea18287894b3d7324d3a270dba6db309eb5517c1b474
+size 3460432416