Instructions to use neuralforgequantum/Qwen3.8-27B-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 neuralforgequantum/Qwen3.8-27B-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 neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf neuralforgequantum/Qwen3.8-27B-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 neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M

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 neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M

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 neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neuralforgequantum/Qwen3.8-27B-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": "neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M

Ollama
How to use neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF with Ollama:
```
ollama run hf.co/neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M
```

Unsloth Studio

How to use neuralforgequantum/Qwen3.8-27B-DFlash2-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 neuralforgequantum/Qwen3.8-27B-DFlash2-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 neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF to start chatting

How to use neuralforgequantum/Qwen3.8-27B-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 neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M

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": "neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF with Docker Model Runner:
```
docker model run hf.co/neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M
```

Lemonade

How to use neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-DFlash2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use neuralforgequantum/Qwen3.8-27B-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 neuralforgequantum/Qwen3.8-27B-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 neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use neuralforgequantum/Qwen3.8-27B-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 neuralforgequantum/Qwen3.8-27B-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 "neuralforgequantum/Qwen3.8-27B-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"

Qwen3.8-27B-DFlash2-GGUF

Blog | GitHub

This repository contains GGUF conversions of incoai/Qwen3.8-27B-DFlash2, the DFlash 2 draft model for Qwen/Qwen3.8-27B. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. The checkpoints are also mirrored at z-lab/Qwen3.8-27B-DFlash2-GGUF.

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
`Qwen3.8-27B-DFlash2-Q4_K_M.gguf`	1.1 GB
`Qwen3.8-27B-DFlash2-Q8_0.gguf`	2.0 GB
`Qwen3.8-27B-DFlash2-BF16.gguf`	3.8 GB

Quick Start

Build llama.cpp with DFlash 2 support (PR #27342):

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
git fetch origin pull/27342/head:pr-27342
git switch pr-27342

# NVIDIA CUDA
cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON
cmake --build build -j

# Apple Silicon
cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_METAL=ON
cmake --build build -j

Then serve:

./build/bin/llama-server \
  -hf ggml-org/Qwen3.8-27B-GGUF:Q4_K_M \
  -hfd incoai/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M \
  --spec-type draft-dflash \
  --spec-draft-n-max 7

See the blog post for other engines and more details.

Evaluation

Target: ggml-org/Qwen3.8-27B-GGUF, Q4_K_M
Sampling: Qwen3.8's officially recommended parameters (temperature 1.0, top-p 0.95, top-k 20), with xhigh reasoning effort
Maximum new tokens: 2048
Prompts: the first eight GSM8K test examples

Acceptance Length

Acceptance length is the per-request mean of completion tokens divided by verification steps. Higher is better.

Draft GGUF	Acceptance Length
BF16	5.28
Q8_0	5.13
Q4_K_M	5.39

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: -

GGUF

Model size

2B params

Architecture

dflash

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for neuralforgequantum/Qwen3.8-27B-DFlash2-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

(629)

this model