Instructions to use Anbeeld/gemma-4-31B-it-DFlash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Anbeeld/gemma-4-31B-it-DFlash-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Anbeeld/gemma-4-31B-it-DFlash-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Anbeeld/gemma-4-31B-it-DFlash-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Anbeeld/gemma-4-31B-it-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 Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Anbeeld/gemma-4-31B-it-DFlash-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 Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Anbeeld/gemma-4-31B-it-DFlash-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 Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Anbeeld/gemma-4-31B-it-DFlash-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 Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Anbeeld/gemma-4-31B-it-DFlash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Anbeeld/gemma-4-31B-it-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": "Anbeeld/gemma-4-31B-it-DFlash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M

SGLang

How to use Anbeeld/gemma-4-31B-it-DFlash-GGUF 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 "Anbeeld/gemma-4-31B-it-DFlash-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Anbeeld/gemma-4-31B-it-DFlash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Anbeeld/gemma-4-31B-it-DFlash-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Anbeeld/gemma-4-31B-it-DFlash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Anbeeld/gemma-4-31B-it-DFlash-GGUF with Ollama:
```
ollama run hf.co/Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Anbeeld/gemma-4-31B-it-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 Anbeeld/gemma-4-31B-it-DFlash-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": "Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Anbeeld/gemma-4-31B-it-DFlash-GGUF with Docker Model Runner:
```
docker model run hf.co/Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M
```

Lemonade

How to use Anbeeld/gemma-4-31B-it-DFlash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-31B-it-DFlash-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Anbeeld/gemma-4-31B-it-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 Anbeeld/gemma-4-31B-it-DFlash-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 Anbeeld/gemma-4-31B-it-DFlash-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Anbeeld/gemma-4-31B-it-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 Anbeeld/gemma-4-31B-it-DFlash-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 "Anbeeld/gemma-4-31B-it-DFlash-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"

Gemma 4 31B IT DFlash GGUF

GGUF quantizations of z-lab DFlash draft model for Gemma 4 31B IT.

Use with BeeLlama.cpp, a llama.cpp fork with advanced quantization features.

gemma-4-31B-it-DFlash

Paper | GitHub | Blog

DFlash is a speculative decoding method that uses a lightweight block diffusion model to draft multiple tokens in parallel. This is the drafter model, which must be paired with google/gemma-4-31B-it.

Quick Start

Installation

vLLM: until Gemma4 DFlash support is merged, install vLLM from PR #41703:

uv pip install -U --torch-backend=auto \
  "vllm @ git+https://github.com/vllm-project/vllm.git@refs/pull/41703/head"

SGLang:

uv pip install "git+https://github.com/sgl-project/sglang.git@refs/pull/23000/head#subdirectory=python"

Launch Server

vLLM:

vllm serve google/gemma-4-31B-it \
  --speculative-config '{"method": "dflash", "model": "z-lab/gemma-4-31B-it-DFlash", "num_speculative_tokens": 15, "attention_backend": "flash_attn"}' \
  --attention-backend triton_attn \
  --max-num-batched-tokens 32768 \
  --trust-remote-code

SGLang:

# Optional: enable schedule overlapping (experimental, may not be stable)
# export SGLANG_ENABLE_SPEC_V2=1
# export SGLANG_ENABLE_DFLASH_SPEC_V2=1
# export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1

python -m sglang.launch_server \
  --model-path google/gemma-4-31B-it \
  --speculative-algorithm DFLASH \
  --speculative-draft-model-path z-lab/gemma-4-31B-it-DFlash \
  --speculative-num-draft-tokens 16 \
  --tp-size 1 \
  --attention-backend triton \
  --speculative-draft-attention-backend fa4 \
  --trust-remote-code

Usage

For vLLM, use port 8000. For SGLang, use port 30000.

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")

response = client.chat.completions.create(
    model="google/gemma-4-31B-it",
    messages=[{"role": "user", "content": "Write a quicksort in Python."}],
    max_tokens=4096,
    temperature=0.0,
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
print(response.choices[0].message.content)

Benchmark Results

Setup: Single NVIDIA B300 GPU per server/run, vLLM, thinking enabled, max output length 4096, greedy decoding.

Throughput and Speedup

DFlash achieves up to 5.8x speedup at concurrency 1.

Generated tokens/sec (speedup vs. autoregressive baseline)

Block Size = 16

Task	Concurrency	AR	DFlash
Math500	1	77	447 (5.8x)
	8	511	2650 (5.2x)
	32	1308	4962 (3.8x)
GSM8K	1	78	408 (5.3x)
	8	520	2321 (4.5x)
	32	1382	4447 (3.2x)
HumanEval	1	76	420 (5.6x)
	8	494	2389 (4.8x)
	32	1145	4139 (3.6x)
MBPP	1	79	343 (4.4x)
	8	535	2036 (3.8x)
	32	1389	3636 (2.6x)
MT-Bench	1	79	236 (3.0x)
	8	503	1334 (2.7x)
	32	1177	2257 (1.9x)

Acceptance Length

Task	c1	c8	c32
Math500	8.59	8.59	8.62
GSM8K	7.53	7.50	7.52
HumanEval	8.00	7.89	7.96
MBPP	6.13	6.13	6.14
MT-Bench	4.23	4.19	4.19

Acknowledgements

Special thanks to David Wang for his outstanding engineering support on this project. We are also grateful to Modal, InnoMatrix, and Yotta Labs for providing the compute resources used to train this draft model.

Citation

If you find DFlash useful, please cite our work. To share feedback on DFlash or request new model support, please fill out this form: DFlash Feedback.

@article{chen2026dflash,
  title   = {{DFlash: Block Diffusion for Flash Speculative Decoding}},
  author  = {Chen, Jian and Liang, Yesheng and Liu, Zhijian},
  journal = {arXiv preprint arXiv:2602.06036},
  year    = {2026}
}

Downloads last month: 5,372

GGUF

Model size

2B params

Architecture

dflash

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Anbeeld/gemma-4-31B-it-DFlash-GGUF

Base model

z-lab/gemma-4-31B-it-DFlash

Quantized

(7)

this model

Collection including Anbeeld/gemma-4-31B-it-DFlash-GGUF

DFlash

Collection

GGUF DFlash draft models for speculative decoding, including Qwen, Kimi, Gemma, and MiniMax. • 24 items • Updated 13 days ago • 1

Paper for Anbeeld/gemma-4-31B-it-DFlash-GGUF

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 99