Instructions to use incoai/Qwen3.8-Flash-Next-DFlash2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use incoai/Qwen3.8-Flash-Next-DFlash2-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 incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use incoai/Qwen3.8-Flash-Next-DFlash2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "incoai/Qwen3.8-Flash-Next-DFlash2-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": "incoai/Qwen3.8-Flash-Next-DFlash2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

Ollama
How to use incoai/Qwen3.8-Flash-Next-DFlash2-GGUF with Ollama:
```
ollama run hf.co/incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M
```
Unsloth Desktop

How to use incoai/Qwen3.8-Flash-Next-DFlash2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use incoai/Qwen3.8-Flash-Next-DFlash2-GGUF with Docker Model Runner:
```
docker model run hf.co/incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M
```

Lemonade

How to use incoai/Qwen3.8-Flash-Next-DFlash2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-DFlash2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use incoai/Qwen3.8-Flash-Next-DFlash2-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 incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

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 incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use incoai/Qwen3.8-Flash-Next-DFlash2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M

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 "incoai/Qwen3.8-Flash-Next-DFlash2-GGUF:Q4_K_M" \
  --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"

Qwen3.8-Flash-Next-DFlash2-GGUF

Blog | GitHub

This repository contains GGUF conversions of incoai/Qwen3.8-Flash-Next-DFlash2, the DFlash 2 draft model for Qwen/Qwen3.8-Flash-Next. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify.

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.

DFlash 2: parallel block drafting with a candidate path selector

File	Size
`Qwen3.8-Flash-Next-DFlash2-Q4_K_M.gguf`	362 MB
`Qwen3.8-Flash-Next-DFlash2-Q5_K_M.gguf`	432 MB
`Qwen3.8-Flash-Next-DFlash2-Q6_K.gguf`	506 MB
`Qwen3.8-Flash-Next-DFlash2-Q8_0.gguf`	652 MB
`Qwen3.8-Flash-Next-DFlash2-BF16.gguf`	1.22 GB

Quick Start

Download a quantization:

hf download incoai/Qwen3.8-Flash-Next-DFlash2-GGUF \
  Qwen3.8-Flash-Next-DFlash2-Q4_K_M.gguf \
  --local-dir ./Qwen3.8-Flash-Next-DFlash2-GGUF

llama.cpp's DFlash 2 support (PR #27342) cannot drive this draft yet. Qwen3.8-Flash-Next carries its hidden state as four hyper-connection streams, and the draft is trained on their mean, which llama.cpp does not compute for the draft yet. Until it does, serve the safetensors checkpoint with SGLang.

See the blog post for other engines and more details.

Evaluation

Acceptance lengths for these GGUFs will be added once llama.cpp supports this target. Full evaluations of the base checkpoint are on the main model card.

Citation

If you find DFlash 2 useful, please cite:

@misc{inco2026dflash2,
  title  = {{DFlash 2: Keep Drafting Parallel}},
  author = {{Inco AI}},
  year   = {2026},
  month  = {August},
  url    = {https://inco.ai/blog/dflash2/}
}

Please also cite the original DFlash paper:

@inproceedings{chen2026dflash,
  title     = {{DFlash: Block Diffusion for Flash Speculative Decoding}},
  author    = {Chen, Jian and Liang, Yesheng and Liu, Zhijian},
  booktitle = {International Conference on Machine Learning (ICML)},
  year      = {2026}
}

Downloads last month: 7,137

GGUF

Model size

0.6B params

Architecture

dflash

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for incoai/Qwen3.8-Flash-Next-DFlash2-GGUF

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

(605)

this model

Collection including incoai/Qwen3.8-Flash-Next-DFlash2-GGUF

DFlash 2

Collection

Keep Drafting Parallel • 11 items • Updated 19 days ago • 54