Instructions to use pipenetwork/Inkling-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/Inkling-MLX-8bit 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("pipenetwork/Inkling-MLX-8bit")
config = load_config("pipenetwork/Inkling-MLX-8bit")

# 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

How to use pipenetwork/Inkling-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 "pipenetwork/Inkling-MLX-8bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "pipenetwork/Inkling-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pipenetwork/Inkling-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 "pipenetwork/Inkling-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 pipenetwork/Inkling-MLX-8bit

Run Hermes

hermes

OpenClaw new

How to use pipenetwork/Inkling-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 "pipenetwork/Inkling-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 "pipenetwork/Inkling-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"

pipenetwork commited on about 3 hours ago

Commit

ecfd4c9

verified ·

1 Parent(s): f741fec

Add NVFP4/MXFP4 quant comparison

Browse files

Files changed (1) hide show

README.md +19 -0

README.md CHANGED Viewed

@@ -35,6 +35,25 @@ multi-token-prediction head is dropped (inference-irrelevant).
 | [6bit](https://huggingface.co/pipenetwork/Inkling-MLX-6bit) | ~717 GB | high quality |
 | [4bit](https://huggingface.co/pipenetwork/Inkling-MLX-4bit) | ~490 GB | balanced default |
 ## ⚠️ Loading requires the bundled `inkling_mlx` loader
 The `inkling_mm_model` architecture is **not** in stock `mlx-lm` / `mlx-vlm`, so this

 | [6bit](https://huggingface.co/pipenetwork/Inkling-MLX-6bit) | ~717 GB | high quality |
 | [4bit](https://huggingface.co/pipenetwork/Inkling-MLX-4bit) | ~490 GB | balanced default |
+## Quantization scheme: affine int4 (not NVFP4 / MXFP4)
+MLX supports FP4 modes and Thinking Machines ships an
+[Inkling-NVFP4](https://huggingface.co/thinkingmachines/Inkling-NVFP4) checkpoint — so for
+the record, we benchmarked round-trip reconstruction error (‖W − Ŵ‖ / ‖W‖ vs bf16) on real
+Inkling expert weights:
+| Scheme | bits/weight | reconstruction error |
+|---|---:|---:|
+| **affine int4** (group 64) | 4.50 | **~9.1%** |
+| nvfp4 (group 16) | 4.50 | ~10.2% |
+| mxfp4 (group 32) | 4.25 | ~12.3% |
+Affine int4 is the most faithful: it is *asymmetric* (per-group scale **and** zero-point, 16
+uniform levels), which centers on Inkling's near-Gaussian expert weights better than
+symmetric FP4's fixed non-uniform levels. FP4's real payoff is heavy-tailed *activations* and
+native Blackwell FP4 tensor cores — neither helps weight fidelity on Apple Silicon, where MLX
+would dequantize FP4 anyway. So these builds use affine int4.
 ## ⚠️ Loading requires the bundled `inkling_mlx` loader
 The `inkling_mm_model` architecture is **not** in stock `mlx-lm` / `mlx-vlm`, so this