Instructions to use suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use suzukimain/Nemotron-Labs-Diffusion-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "suzukimain/Nemotron-Labs-Diffusion-8B-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": "suzukimain/Nemotron-Labs-Diffusion-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M

Ollama
How to use suzukimain/Nemotron-Labs-Diffusion-8B-GGUF with Ollama:
```
ollama run hf.co/suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M
```

Unsloth Studio

How to use suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for suzukimain/Nemotron-Labs-Diffusion-8B-GGUF to start chatting

How to use suzukimain/Nemotron-Labs-Diffusion-8B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf suzukimain/Nemotron-Labs-Diffusion-8B-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": "suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-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 suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use suzukimain/Nemotron-Labs-Diffusion-8B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf suzukimain/Nemotron-Labs-Diffusion-8B-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 "suzukimain/Nemotron-Labs-Diffusion-8B-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"

Docker Model Runner
How to use suzukimain/Nemotron-Labs-Diffusion-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M
```

Lemonade

How to use suzukimain/Nemotron-Labs-Diffusion-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull suzukimain/Nemotron-Labs-Diffusion-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nemotron-Labs-Diffusion-8B-GGUF-Q4_K_M

List all available models

lemonade list

Nemotron-Labs-Diffusion-8B — GGUF

GGUF quantizations of nvidia/Nemotron-Labs-Diffusion-8B, a tri-mode (autoregressive / diffusion / self-speculation) block-diffusion language model.

⚠️ Requires a diffusion-aware llama.cpp fork

Mainline llama.cpp cannot convert or run this architecture. Use spiritbuun/buun-llama-cpp — its converter maps NemotronLabsDiffusionModel to the GGUF dream architecture.

Files

File	Size
`Nemotron-Labs-Diffusion-8B-Q4_K_M.gguf`	4.84 GB
`Nemotron-Labs-Diffusion-8B-Q5_K_M.gguf`	5.64 GB

Run

Diffusion (dlm):

llama-diffusion-cli -m Nemotron-Labs-Diffusion-8B-Q4_K_M.gguf -ngl 99 -fa on -p "your prompt" \
  --diffusion-block-length 32 --diffusion-steps 128 --diffusion-threshold 0.9 -ub 512

Self-speculation:

llama-diffusion-cli -m Nemotron-Labs-Diffusion-8B-Q4_K_M.gguf -ngl 99 -fa on -p "your prompt" \
  --diffusion-self-spec --diffusion-block-length 32 --diffusion-draft-length 16 --diffusion-steps 128

OpenAI-compatible server (auto-enables self-speculation = AR-equivalent):

llama-server -m Nemotron-Labs-Diffusion-8B-Q4_K_M.gguf -ngl 99 -c 4096 -fa on --port 8080

Benchmarks (single 16 GB-VRAM GPU, Q4_K_M unless noted)

Model	Engine / mode	tok/s	TTFT	First-visible	VRAM (weights)	GPU total	Streaming	Quality
gemma-4-E4B	Ollama (AR)	148.7	0.03s	~0.05s	3.11 GB	6.28 GB	◎ per-token	good
gemma-4-12B	Ollama (AR)	84.4	0.04s	~0.06s	7.27 GB	9.69 GB	◎ per-token	good (clean numbered list)
Nemotron-8B Q4	buun dlm	69.4	—	~0.53s	4.84 GB	~7.0 GB	△ block-wise	good (slightly rough)
Nemotron-8B Q5	buun dlm	58.7	—	~0.56s	5.64 GB	~7.5 GB	△ block-wise	good
Nemotron-8B Q4	llama-server	~46	prefill 454/s	streams*	4.84 GB	~7.0 GB	→ reasoning_content	good

First-visible = time until the first text can actually be shown (warm). AR streams from the first token (≈ TTFT); block diffusion must finish the first 32-token block before anything is displayable, so its first-visible (~0.5 s) is much higher than its TTFT suggests.
*The server (self-spec) streams per accepted chunk, but the answer is gated behind reasoning_content.
gemma-4 rows are public autoregressive GGUFs measured on the same GPU for reference.

Text-quality comparison

Same prompt, chat-templated, temp 0.7 — "犬と猫の違いを3つ、箇条書きで簡潔に教えてください。" (3 bullet points contrasting dogs vs cats). Nemotron via llama-server (answer in reasoning_content).

Model	Output excerpt	Follows format / contrast
gemma-4-12B	群れの性質：犬は「群れ」で行動し飼い主を家族として従う。一方、猫は「単独」で自立心が強い…	✓ clean 3-bullet contrast
gemma-4-E4B	犬は群れ（家族）を意識し指示に従う傾向。一方、猫は単独行動を好み自立した性質…	✓ clean
Nemotron-8B Q5	犬は社会的で家族との絆が強い。犬は遊びに応じ行動を変える…（犬中心で対比が弱い）	△ weaker contrast
Nemotron-14B Q5	食べ方：犬は肉食動物として肉を食べる。猫も肉食だが自分で捕まえて食べる…（やや冗長）	◯ but slightly circular

Empathy prompt ("最近ちょっと疲れてるんだ。やさしく励まして。"): all four give warm, fluent replies.

Takeaway: all produce fluent Japanese. The optimized autoregressive gemma-4 models follow structured instructions most cleanly; the Nemotron diffusion models are coherent but a bit rougher (more repetition / weaker factual contrast). Small single-prompt sample — treat as indicative, not a leaderboard.

Modes / caveats

diffusion (dlm) and self-speculation both run via llama-diffusion-cli.
llama-server auto-detects the model and runs self-speculation (diffusion draft + AR verify, lossless vs. AR at temperature 0). This is the AR path for GGUF.
Self-speculation gives no speedup over plain block diffusion on a single 16 GB consumer GPU (its benefit appears on large datacenter GPUs).
The generic llama-cli does not work with this dream arch (it hangs) — use llama-server or llama-diffusion-cli.
llama-server emits the answer in reasoning_content; route it to content with the appropriate --reasoning option.
Optimized AR GGUFs (e.g. gemma-4) are faster and stream per-token; this model emits 32-token blocks.

License

Derivative of NVIDIA's model — governed by the NVIDIA Open Model License.

Credits

Original model: NVIDIA — nvidia/Nemotron-Labs-Diffusion-8B
Diffusion-aware llama.cpp fork & 14B GGUF: spiritbuun

Downloads last month: 207

GGUF

Model size

8B params

Architecture

dream

Hardware compatibility

4-bit

5-bit

Model tree for suzukimain/Nemotron-Labs-Diffusion-8B-GGUF

Base model

nvidia/Nemotron-Labs-Diffusion-8B

Quantized

(1)

this model