Instructions to use AtomicChat/Qwen3-Coder-Next-DFlash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AtomicChat/Qwen3-Coder-Next-DFlash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AtomicChat/Qwen3-Coder-Next-DFlash-GGUF",
	filename="Qwen3-Coder-Next-DFlash.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AtomicChat/Qwen3-Coder-Next-DFlash-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 AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_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 AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_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 AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0

Use Docker

docker model run hf.co/AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use AtomicChat/Qwen3-Coder-Next-DFlash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/Qwen3-Coder-Next-DFlash-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AtomicChat/Qwen3-Coder-Next-DFlash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0

Ollama
How to use AtomicChat/Qwen3-Coder-Next-DFlash-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0
```

Unsloth Studio

How to use AtomicChat/Qwen3-Coder-Next-DFlash-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 AtomicChat/Qwen3-Coder-Next-DFlash-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 AtomicChat/Qwen3-Coder-Next-DFlash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AtomicChat/Qwen3-Coder-Next-DFlash-GGUF to start chatting

How to use AtomicChat/Qwen3-Coder-Next-DFlash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_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": "AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AtomicChat/Qwen3-Coder-Next-DFlash-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 AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_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 AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use AtomicChat/Qwen3-Coder-Next-DFlash-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_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 "AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_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 AtomicChat/Qwen3-Coder-Next-DFlash-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0
```

Lemonade

How to use AtomicChat/Qwen3-Coder-Next-DFlash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Qwen3-Coder-Next-DFlash-GGUF:Q8_0

Run and chat with the model

lemonade run user.Qwen3-Coder-Next-DFlash-GGUF-Q8_0

List all available models

lemonade list

Draft: z-lab/Qwen3-Coder-Next-DFlash · Target: Qwen/Qwen3-Coder-Next

Qwen3-Coder Next DFlash, the DFlash speculative-decoding draft converted to GGUF by Atomic Chat. Built straight from z-lab's original weights. Runs fully offline.

What this is

DFlash is a speculative-decoding method that drafts a whole block of candidate tokens in a single forward pass using a lightweight block-diffusion model, instead of one token at a time. This repo is the draft component only — it does nothing on its own. You run it alongside the target model Qwen/Qwen3-Coder-Next, which verifies the drafted block and keeps the longest correct prefix. Output is identical to running the target alone, just faster.

These GGUFs are converted from z-lab's original weights, not a repack of someone else's GGUF. The draft attaches to any GGUF of the target model (Atomic, unsloth, bartowski, ...).

Run in llama.cpp

Needs a build of llama.cpp with DFlash speculative decoding (PR #22105). You supply the target as -m and this draft as -md:

./llama-server \
    -m   Qwen3-Coder-Next.gguf \
    -md  Qwen3-Coder-Next-DFlash.Q8_0.gguf \
    --spec-type draft-dflash --spec-draft-n-max 15 \
    -ngl 99 -fa on --jinja -c 8192

DFlash is trained for non-thinking generation — pass enable_thinking=false in the chat template for best acceptance.

Choosing a quant

Quant	Size	Notes
`Q8_0`	0.51 GB	Recommended. Near-lossless draft head, small and fast to draft with.

Performance

z-lab report up to 6.17x lossless acceleration on their reference stack (vLLM / SGLang / Transformers). In llama.cpp today the DFlash port is newer: in our tests dense targets get roughly 1.8x-2.8x end-to-end on code generation, and acceptance climbs on larger targets and structured/code output. Acceptance and speedup depend on the target and the content, not on the quantization. Speedups shrink on free-form prose and on small-active MoE targets.

License

Released by z-lab under the MIT license. Converted to GGUF by Atomic Chat. See the DFlash paper and project page.

Downloads last month: 111

GGUF

Model size

0.5B params

Architecture

dflash

Hardware compatibility

8-bit

Model tree for AtomicChat/Qwen3-Coder-Next-DFlash-GGUF

Base model

z-lab/Qwen3-Coder-Next-DFlash

Quantized

(2)

this model

Paper for AtomicChat/Qwen3-Coder-Next-DFlash-GGUF

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 89