Instructions to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF",
	filename="qwen35-4b-dflash-Q4_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Use Docker

docker model run hf.co/shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

LM Studio
Jan
Ollama
How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with Ollama:
```
ollama run hf.co/shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0
```

Unsloth Studio

How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF to start chatting

How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with Docker Model Runner:
```
docker model run hf.co/shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0
```

Lemonade

How to use shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF:Q4_0

Run and chat with the model

lemonade run user.Qwen3.5-4B-DFlash-Q4_0-GGUF-Q4_0

List all available models

lemonade list

Qwen3.5-4B-DFlash — Q4_0 GGUF (draft model)

A Q4_0 GGUF of the z-lab/Qwen3.5-4B-DFlash block-diffusion draft model for DFlash speculative decoding with the Qwen3.5-4B target. This is not a standalone language model — it must be paired with the Qwen3.5-4B target in a DFlash-capable llama.cpp server.

Files

File	Size (bytes)	SHA256
`qwen35-4b-dflash-Q4_0.gguf`	367,939,840	`2772878B6B2B4E607C42BFCEE5A429B54BE27F7A57E86A3108E9E437CB5C79FF`

69 tensors total: 43 2-D weight tensors are Q4_0, the remaining 26 (norms, etc.) are F32.

Provenance

Source: z-lab/Qwen3.5-4B-DFlash, HF revision 9a1996ccf887b79ab3af4fcbf8c1d1f4b5658bcf (model.safetensors SHA256 1EB221D36ABB13A5F1B972F8D031A9723FAD8CBB7D275ABE548B60E77577EB42).
Conversion: upstream llama.cpp convert_hf_to_gguf.py with the DFlash support merged in ggml-org/llama.cpp#22105, sourcing the tokenizer from the Qwen3.5-4B target via --target-model-dir. safetensors → BF16 GGUF → llama-quantize Q4_0.
The BF16 intermediate is 1,279,873,280 bytes.

Architecture / GGUF metadata

general.architecture = dflash
6 layers: 5 sliding_attention + 1 full_attention (sliding_window = 4096)
hidden 2560, FFN 9216, 32 Q heads / 8 KV heads, head dim 128
dflash.block_size = 16
dflash.target_layers = [2, 6, 10, 14, 18, 22, 26, 30] (llama.cpp layer-input semantics; the source dflash_config.target_layer_ids are [1, 5, 9, 13, 17, 21, 25, 29])
tokenizer.ggml.mask_token_id = 248077, vocab size 248320 (shares the Qwen3.5-4B vocab)

The draft is only the DFlash core; at runtime it borrows the target's token embedding and tied output projection.

Usage (sketch)

Run against the Qwen3.5-4B target in a DFlash-capable llama.cpp server, e.g.:

llama-server \
  -m Qwen3.5-4B-Q4_0.gguf \
  --spec-draft-model qwen35-4b-dflash-Q4_0.gguf \
  --spec-type draft-dflash --spec-draft-n-max 7

DFlash speculative decoding is not part of stock upstream llama.cpp runtime; use a build with DFlash runtime support.

License

Inherits the terms of the base model — see z-lab/Qwen3.5-4B-DFlash.

Downloads last month: 134

GGUF

Model size

0.6B params

Architecture

dflash

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for shujunyi/Qwen3.5-4B-DFlash-Q4_0-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

z-lab/Qwen3.5-4B-DFlash

Quantized

(6)

this model