Instructions to use netprojects/SenseNova-Loop-9B-Preview-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-8bit 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-8bit")

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-8bit 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-8bit"

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-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-8bit 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-8bit"

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-8bit"
# 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-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-8bit 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-8bit"

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-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use netprojects/SenseNova-Loop-9B-Preview-MLX-8bit 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-8bit"

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-8bit" \
  --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"

Paris99 commited on about 10 hours ago

Commit

bee0f79

verified ·

1 Parent(s): a8e5503

Card: GitHub link and sizes

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ tags: [mlx, sensenova, sensenova-loop, looped-transformer, mhc, qwen3_5, apple-s
 ---
 # SenseNova-Loop-9B-Preview — MLX 8-bit
-An 8-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. 8.9 GB of weights. Text model; image input is not part of this build yet. Practically identical to SenseNova's original weights; the recommended build.
 Published by [NetProjects](https://netprojects.com) (Internet Projects Ltd). Not affiliated with SenseTime / SenseNova.
@@ -19,7 +19,7 @@ SenseNova-Loop is a Qwen3.5-based model with two additions, and this build runs
 - **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`.
 ## Results (MacBook Pro M5 Max, 128 GB, 7 November 2026)
@@ -29,7 +29,7 @@ Agreement with SenseNova's own PyTorch code (Transformers 5.18, bf16) on 16 prom
 |---|---|---|---|
 | 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 | 8.9 GB | 6.8 GB | 4.7 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):
@@ -59,7 +59,7 @@ 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-8bit --trust-remote-code`.
-**Other sizes:** [6-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-Preview-MLX-6bit) (6.8 GB) · [4-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-Preview-MLX-4bit) (4.7 GB)
 ## License

 ---
 # SenseNova-Loop-9B-Preview — MLX 8-bit
+An 8-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. 9.6 GB of weights. Text model; image input is not part of this build yet. Practically identical to SenseNova's original weights; the recommended build.
 Published by [NetProjects](https://netprojects.com) (Internet Projects Ltd). Not affiliated with SenseTime / SenseNova.
 - **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)
 |---|---|---|---|
 | 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):
 Set `enable_thinking=True` for thinking mode. Server: `mlx_lm.server --model netprojects/SenseNova-Loop-9B-Preview-MLX-8bit --trust-remote-code`.
+**Other sizes:** [6-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-Preview-MLX-6bit) (7.3 GB) · [4-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-Preview-MLX-4bit) (5.1 GB)
 ## License