Instructions to use netprojects/SenseNova-Loop-9B-Preview-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("netprojects/SenseNova-Loop-9B-Preview-MLX-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-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 "netprojects/SenseNova-Loop-9B-Preview-MLX-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": "netprojects/SenseNova-Loop-9B-Preview-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "netprojects/SenseNova-Loop-9B-Preview-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "netprojects/SenseNova-Loop-9B-Preview-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "netprojects/SenseNova-Loop-9B-Preview-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-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 "netprojects/SenseNova-Loop-9B-Preview-MLX-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 netprojects/SenseNova-Loop-9B-Preview-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-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 "netprojects/SenseNova-Loop-9B-Preview-MLX-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 "netprojects/SenseNova-Loop-9B-Preview-MLX-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-Preview-MLX-4bit / README.md

Paris99

Card: Python 3.11+ (mlx-lm 0.32 requires it)

6cde923 verified about 10 hours ago

preview code

Raw History Blame Contribute Delete

4.59 kB

---
license: apache-2.0
base_model: sensenova/SenseNova-Loop-9B-Preview
base_model_relation: quantized
library_name: mlx
pipeline_tag: text-generation
tags: [mlx, sensenova, sensenova-loop, looped-transformer, mhc, qwen3_5, apple-silicon]
---
# SenseNova-Loop-9B-Preview — MLX 4-bit

A 4-bit MLX conversion (affine, group size 64) of [sensenova/SenseNova-Loop-9B-Preview](https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview) (revision `9937e91`, released 30 October 2026) for Apple Silicon. 5.1 GB of weights. Text model; image input is not part of this build yet. The smallest build. It follows the reference less closely than 8-bit and 6-bit (89% same top token); pick 6-bit or 8-bit when quality matters most.

Published by [NetProjects](https://netprojects.com) (Internet Projects Ltd). Not affiliated with SenseTime / SenseNova.

## A faithful port of the looped architecture

SenseNova-Loop is a Qwen3.5-based model with two additions, and this build runs both exactly as SenseNova's own code does:

- **Looped execution:** layers 0–3 run once, layers 4–27 run **twice** with shared weights, then layers 28–31: 56 layer passes per token. Every pass has its own cache slot (KV cache for full attention, conv and recurrent state for Gated DeltaNet).
- **Two-stream mHC** on layers 4–27: the hidden state is split into two residual streams that are routed by small float32 routers (pre / post gates and a 2×2 Sinkhorn mixing matrix, 20 iterations). The 96 router tensors stay in float32 and are never quantized.

The model code is `sensenova_loop.py`, included in this repo and loaded by mlx-lm through `trust_remote_code=True`. Source, converter, parity and benchmark scripts: [github.com/internet-projects/sensenova-loop-mlx](https://github.com/internet-projects/sensenova-loop-mlx).

## Results (MacBook Pro M5 Max, 128 GB, 7 November 2026)

Agreement with SenseNova's own PyTorch code (Transformers 5.18, bf16) on 16 prompts, every position:

| | 8-bit | 6-bit | 4-bit |
|---|---|---|---|
| Same top token as the reference | 97.6% | 97.2% | 89.2% |
| KL divergence at the last token | 0.0011 | 0.0037 | 0.064 |
| Size | 9.6 GB | 7.3 GB | 5.1 GB |

Short public benchmark (same harness for every build; first 300 ARC-Challenge test questions, log-likelihood over the 4 choices; first 50 GSM8K test questions, chat template, thinking off, greedy):

| | bf16 | 8-bit | 6-bit | 4-bit |
|---|---|---|---|---|
| ARC-Challenge acc / acc_norm | 48.7 / 51.0 | 48.7 / 50.3 | 47.7 / 49.0 | 45.7 / 45.0 |
| GSM8K (50) | – | 94.0 | 88.0 | 92.0 |
GSM8K on 50 questions moves 2 points per question.
Decode speed for this build: about 22 tokens/s on the M5 Max (short run). The loop doubles the work of the middle 24 layers, so it is slower than a plain 9B model; that is the cost of the extra depth.
## Use
Needs Python 3.11 or newer and mlx-lm 0.32 or newer (the macOS system Python 3.9 only gets an older mlx-lm that can't load this model).
```bash
pip install -U "mlx-lm>=0.32"
```
```python
from mlx_lm import load, generate

model, tokenizer = load("netprojects/SenseNova-Loop-9B-Preview-MLX-4bit", trust_remote_code=True)
messages = [{"role": "user", "content": "Explain in two sentences why the sky is blue."}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False)
print(generate(model, tokenizer, prompt=prompt, max_tokens=256))
```
Set `enable_thinking=True` for thinking mode. Server: `mlx_lm.server --model netprojects/SenseNova-Loop-9B-Preview-MLX-4bit --trust-remote-code`.
**Other sizes:** [8-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-Preview-MLX-8bit) (9.6 GB) · [6-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-Preview-MLX-6bit) (7.3 GB)
## License
SenseNova-Loop-9B-Preview is released by SenseNova under the **Apache License 2.0** (`LICENSE` included). This repository contains converted and quantized weights of that model (modified from the original: converted to MLX format and quantized to 4-bit) and an MLX implementation of its architecture, distributed under the same license.
Credits: SenseNova / SenseTime (SenseNova-Loop-9B-Preview), Qwen team (Qwen3.5), Apple MLX and mlx-lm. Conversion and MLX port by Paris Michalas, Partner at [NetProjects](https://netprojects.com). Not affiliated with SenseTime / SenseNova.
**More NetProjects MLX builds:** [NetProjects MLX builds collection](https://huggingface.co/collections/netprojects/netprojects-mlx-builds-6ae3b2683a59a1b4fc4c0c3a) · [all models at huggingface.co/netprojects](https://huggingface.co/netprojects)

	---
	license: apache-2.0
	base_model: sensenova/SenseNova-Loop-9B-Preview
	base_model_relation: quantized
	library_name: mlx
	pipeline_tag: text-generation
	tags: [mlx, sensenova, sensenova-loop, looped-transformer, mhc, qwen3_5, apple-silicon]
	---
	# SenseNova-Loop-9B-Preview — MLX 4-bit

	A 4-bit MLX conversion (affine, group size 64) of [sensenova/SenseNova-Loop-9B-Preview](https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview) (revision `9937e91`, released 30 October 2026) for Apple Silicon. 5.1 GB of weights. Text model; image input is not part of this build yet. The smallest build. It follows the reference less closely than 8-bit and 6-bit (89% same top token); pick 6-bit or 8-bit when quality matters most.

	Published by [NetProjects](https://netprojects.com) (Internet Projects Ltd). Not affiliated with SenseTime / SenseNova.

	## A faithful port of the looped architecture

	SenseNova-Loop is a Qwen3.5-based model with two additions, and this build runs both exactly as SenseNova's own code does:

	- Looped execution: layers 0–3 run once, layers 4–27 run twice with shared weights, then layers 28–31: 56 layer passes per token. Every pass has its own cache slot (KV cache for full attention, conv and recurrent state for Gated DeltaNet).
	- Two-stream mHC on layers 4–27: the hidden state is split into two residual streams that are routed by small float32 routers (pre / post gates and a 2×2 Sinkhorn mixing matrix, 20 iterations). The 96 router tensors stay in float32 and are never quantized.

	The model code is `sensenova_loop.py`, included in this repo and loaded by mlx-lm through `trust_remote_code=True`. Source, converter, parity and benchmark scripts: [github.com/internet-projects/sensenova-loop-mlx](https://github.com/internet-projects/sensenova-loop-mlx).

	## Results (MacBook Pro M5 Max, 128 GB, 7 November 2026)

	Agreement with SenseNova's own PyTorch code (Transformers 5.18, bf16) on 16 prompts, every position:

	\| \| 8-bit \| 6-bit \| 4-bit \|
	\|---\|---\|---\|---\|
	\| Same top token as the reference \| 97.6% \| 97.2% \| 89.2% \|
	\| KL divergence at the last token \| 0.0011 \| 0.0037 \| 0.064 \|
	\| Size \| 9.6 GB \| 7.3 GB \| 5.1 GB \|

	Short public benchmark (same harness for every build; first 300 ARC-Challenge test questions, log-likelihood over the 4 choices; first 50 GSM8K test questions, chat template, thinking off, greedy):

	\| \| bf16 \| 8-bit \| 6-bit \| 4-bit \|
	\|---\|---\|---\|---\|---\|
	\| ARC-Challenge acc / acc_norm \| 48.7 / 51.0 \| 48.7 / 50.3 \| 47.7 / 49.0 \| 45.7 / 45.0 \|
	\| GSM8K (50) \| – \| 94.0 \| 88.0 \| 92.0 \|

	GSM8K on 50 questions moves 2 points per question.

	Decode speed for this build: about 22 tokens/s on the M5 Max (short run). The loop doubles the work of the middle 24 layers, so it is slower than a plain 9B model; that is the cost of the extra depth.

	## Use

	Needs Python 3.11 or newer and mlx-lm 0.32 or newer (the macOS system Python 3.9 only gets an older mlx-lm that can't load this model).

	```bash
	pip install -U "mlx-lm>=0.32"
	```

	```python
	from mlx_lm import load, generate

	model, tokenizer = load("netprojects/SenseNova-Loop-9B-Preview-MLX-4bit", trust_remote_code=True)
	messages = [{"role": "user", "content": "Explain in two sentences why the sky is blue."}]
	prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False)
	print(generate(model, tokenizer, prompt=prompt, max_tokens=256))
	```

	Set `enable_thinking=True` for thinking mode. Server: `mlx_lm.server --model netprojects/SenseNova-Loop-9B-Preview-MLX-4bit --trust-remote-code`.

	Other sizes: [8-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-Preview-MLX-8bit) (9.6 GB) · [6-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-Preview-MLX-6bit) (7.3 GB)

	## License

	SenseNova-Loop-9B-Preview is released by SenseNova under the Apache License 2.0 (`LICENSE` included). This repository contains converted and quantized weights of that model (modified from the original: converted to MLX format and quantized to 4-bit) and an MLX implementation of its architecture, distributed under the same license.

	Credits: SenseNova / SenseTime (SenseNova-Loop-9B-Preview), Qwen team (Qwen3.5), Apple MLX and mlx-lm. Conversion and MLX port by Paris Michalas, Partner at [NetProjects](https://netprojects.com). Not affiliated with SenseTime / SenseNova.

	More NetProjects MLX builds: [NetProjects MLX builds collection](https://huggingface.co/collections/netprojects/netprojects-mlx-builds-6ae3b2683a59a1b4fc4c0c3a) · [all models at huggingface.co/netprojects](https://huggingface.co/netprojects)