Instructions to use guideboardlabs/SenseNova-Loop-9B-Preview-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 guideboardlabs/SenseNova-Loop-9B-Preview-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 guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf guideboardlabs/SenseNova-Loop-9B-Preview-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 guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf guideboardlabs/SenseNova-Loop-9B-Preview-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 guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M

Use Docker

docker model run hf.co/guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use guideboardlabs/SenseNova-Loop-9B-Preview-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "guideboardlabs/SenseNova-Loop-9B-Preview-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": "guideboardlabs/SenseNova-Loop-9B-Preview-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M

Ollama
How to use guideboardlabs/SenseNova-Loop-9B-Preview-GGUF with Ollama:
```
ollama run hf.co/guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M
```
Unsloth Desktop

How to use guideboardlabs/SenseNova-Loop-9B-Preview-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf guideboardlabs/SenseNova-Loop-9B-Preview-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": "guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use guideboardlabs/SenseNova-Loop-9B-Preview-GGUF with Docker Model Runner:
```
docker model run hf.co/guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M
```

Lemonade

How to use guideboardlabs/SenseNova-Loop-9B-Preview-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SenseNova-Loop-9B-Preview-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use guideboardlabs/SenseNova-Loop-9B-Preview-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 guideboardlabs/SenseNova-Loop-9B-Preview-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 guideboardlabs/SenseNova-Loop-9B-Preview-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use guideboardlabs/SenseNova-Loop-9B-Preview-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf guideboardlabs/SenseNova-Loop-9B-Preview-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 "guideboardlabs/SenseNova-Loop-9B-Preview-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"

SenseNova Loop 9B Preview — GGUF

Text-only GGUF quants of sensenova/SenseNova-Loop-9B-Preview. Weights, training and the model itself are SenseNova / OpenSenseNova's work. This repository only converts and quantizes.

Stock llama.cpp cannot load these. The architecture is sensenova_loop, implemented in the runtime fork https://github.com/GuideboardLabs/llama.cpp-sensenova-loop (branch sensenova-loop, two commits, patches included). Vision and MTP are not part of the export; text chat only.

Files

file	quant	size
`SenseNova-Loop-9B-Preview-Q4_0.gguf`	Q4_0	5,325,947,040 B
`SenseNova-Loop-9B-Preview-Q4_K_M.gguf`	Q4_K_M	5,628,723,360 B
`SenseNova-Loop-9B-Preview-Q3_K_M.gguf`	Q3_K_M	4,642,406,560 B

Convolution kernels, norms and the mHC router weights stay FP32; everything else is quantized.

The looped block is stored once. The runtime aliases the second visit of those layers onto the first, which is numerically identical and 36 percent smaller than storing the block twice.

Run

GGML_VK_DISABLE_HOST_VISIBLE_VIDMEM=1 ./build/bin/llama-server \
    -m SenseNova-Loop-9B-Preview-Q4_0.gguf -ngl 99 -c 4096 -fa on --port 8080

The environment variable matters on small-BAR cards: without it the recurrent state buffers land in host-visible memory. It only takes effect once the model fits in VRAM.

Measured

RX 5700 XT (NAVI10), 4096 context, full offload, temperature 0:

quant	decode	prompt
Q4_0	31.4 t/s	29.6 t/s
Q4_K_M	30.5 t/s	30.5 t/s
Q3_K_M	29.9 t/s	19.4 t/s

Q3_K_M is slower than Q4_0 despite a smaller file: RDNA1 has no integer dot product, so the K-quant decode costs more than the bytes it saves.

Accuracy

Greedy decoding matches the reference transformers implementation token for token on the development prompt (The capital of France is, temperature 0), and the custom routing ops agree with their CPU implementation to 1.2e-7. No KL or perplexity sweep has been run on these quants.

Context was exercised to 16K tokens here; the upstream model advertises 262K, which we have not validated.

Downloads last month: 3,905

GGUF

Model size

9B params

Architecture

sensenova_loop

Hardware compatibility

3-bit

4-bit

Model tree for guideboardlabs/SenseNova-Loop-9B-Preview-GGUF

Base model

sensenova/SenseNova-Loop-9B-Preview

Quantized

(9)

this model