Instructions to use nativ-community/SenseNova-Loop-9B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use nativ-community/SenseNova-Loop-9B-4bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("nativ-community/SenseNova-Loop-9B-4bit") config = load_config("nativ-community/SenseNova-Loop-9B-4bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use nativ-community/SenseNova-Loop-9B-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "nativ-community/SenseNova-Loop-9B-4bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "nativ-community/SenseNova-Loop-9B-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use nativ-community/SenseNova-Loop-9B-4bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "nativ-community/SenseNova-Loop-9B-4bit"
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 nativ-community/SenseNova-Loop-9B-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use nativ-community/SenseNova-Loop-9B-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "nativ-community/SenseNova-Loop-9B-4bit"
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 "nativ-community/SenseNova-Loop-9B-4bit" \ --custom-provider-id mlx-lm \ --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 — 4bit MLX
An MLX conversion of sensenova/SenseNova-Loop-9B, supporting text and image inputs with text output on Apple silicon.
Precision and architecture
Eligible language projections and embeddings use 4-bit affine quantization, group size 64. The vision tower stays BF16. The mHC router weights and biases remain FP32 and match the source checkpoint exactly. Weight files occupy 5.963 GB (5.553 GiB).
The 32 physical decoder layers execute as 56 visits, each with an independent cache. The unused training-only loop gate is omitted.
Usage
Requires MLX-VLM with SenseNova Loop support (PR #2752). Install this validated implementation revision if your installed release does not include it:
python -m pip install -U "git+https://github.com/Neywa-Labs/mlx-vlm.git@3e90e9d9628ab386ff8dfbe561b09859cad9e3b9"
python -m mlx_vlm generate --model nativ-community/SenseNova-Loop-9B-4bit --prompt "What is 17 plus 25?" --max-tokens 128
python -m mlx_vlm generate --model nativ-community/SenseNova-Loop-9B-4bit --image image.jpg --prompt "Describe this image." --max-tokens 256
from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
model, processor = load("nativ-community/SenseNova-Loop-9B-4bit")
images = ["image.jpg"]
prompt = apply_chat_template(
processor, model.config, "Describe this image.",
num_images=len(images), enable_thinking=False,
)
result = generate(model, processor, prompt, image=images, max_tokens=256)
print(result.text)
Use enable_thinking=True for the model's thinking template. Multiple images use the ordered image list and num_images=len(images).
Conversion
Converted directly from the original floating-point checkpoint at revision 329a65f, using MLX 0.32.4:
python -m mlx_vlm convert --hf-path sensenova/SenseNova-Loop-9B --revision 329a65f701ba8c48b73c30d0cbaa6f0449733673 --mlx-path SenseNova-Loop-9B-4bit --dtype bfloat16 -q --q-bits 4 --q-group-size 64 --q-mode affine
Validation and limits
This export was reloaded and tested with greedy text generation and image description on an Apple M5 Max with 128 GB unified memory. The arithmetic check returned 42; the image check identified cats. All 96 mHC routing tensors remain byte-identical to the source FP32 tensors.
These are smoke checks, not a quality benchmark. The full 512K context limit has not been validated. The Qwen3.5 fused speculative verifier is unsupported and is rejected by the implementation.
Source
See the original model card for model details and upstream Apache-2.0 licensing information.
- Downloads last month
- -
4-bit
Model tree for nativ-community/SenseNova-Loop-9B-4bit
Base model
sensenova/SenseNova-Loop-9B