Instructions to use avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw 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("avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw")
config = load_config("avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw")

# 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 avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw"

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": "avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw 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 "avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw"

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 avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw"

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 "avlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw" \
  --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"

avlp12 commited on Jul 21

Commit

8994ede

verified ·

1 Parent(s): 37ec3a0

Link live Q6 two-box sibling

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ base_model_relation: quantized
 # Inkling-975B-Alis-MLX-Dynamic-3.7bpw
-> The **quality / golden-spot** tier of the Inkling · Alis MLX Dynamic family — siblings: the [\~2.7 bpw size-optimal build](https://huggingface.co/avlp12/Inkling-975B-Alis-MLX-Dynamic-2.7bpw) and a \~6.5 bpw two-box Q6 performance build (uploading as its certification completes). Full family: [Inkling 975B · Alis MLX Dynamic collection](https://huggingface.co/collections/avlp12/inkling-975b-alis-mlx-dynamic-6a5f2d32de21740f9fdfc390).
 **Apple Silicon (MLX) mixed-precision quantization of [thinkingmachines/Inkling](https://huggingface.co/thinkingmachines/Inkling)** — a 975B-class multimodal Mixture-of-Experts model (66 hybrid decoder layers, **256 routed experts (top-6) + 2 shared** per MoE layer, hidden 6144, sliding-window attention + short-convolution hybrid, vision + audio front-ends, 201K vocab).
@@ -79,7 +79,7 @@ The result is conservative by construction: **you get provably-not-worse-than-ba
 |---|---|---|---|
 | **this** — quality / golden spot | **3.71** | 409 GiB | single 512 GB Mac, best quality in one box |
 | [capacity / size-optimal](https://huggingface.co/avlp12/Inkling-975B-Alis-MLX-Dynamic-2.7bpw) | 2.72 | 299 GiB | single Mac with generous headroom / smaller boxes |
-| Q6 teacher (two-box) | \~6.5 | \~790 GiB | maximum fidelity, 2 × 512 GB pipeline serving |
 ---

 # Inkling-975B-Alis-MLX-Dynamic-3.7bpw
+> The **quality / golden-spot** tier of the Inkling · Alis MLX Dynamic family — siblings: the [\~2.7 bpw size-optimal build](https://huggingface.co/avlp12/Inkling-975B-Alis-MLX-Dynamic-2.7bpw) and the [\~6.6 bpw two-box Q6 performance build](https://huggingface.co/avlp12/Inkling-975B-Alis-MLX-Dynamic-6.6bpw). Full family: [Inkling 975B · Alis MLX Dynamic collection](https://huggingface.co/collections/avlp12/inkling-975b-alis-mlx-dynamic-6a5f2d32de21740f9fdfc390).
 **Apple Silicon (MLX) mixed-precision quantization of [thinkingmachines/Inkling](https://huggingface.co/thinkingmachines/Inkling)** — a 975B-class multimodal Mixture-of-Experts model (66 hybrid decoder layers, **256 routed experts (top-6) + 2 shared** per MoE layer, hidden 6144, sliding-window attention + short-convolution hybrid, vision + audio front-ends, 201K vocab).
 |---|---|---|---|
 | **this** — quality / golden spot | **3.71** | 409 GiB | single 512 GB Mac, best quality in one box |
 | [capacity / size-optimal](https://huggingface.co/avlp12/Inkling-975B-Alis-MLX-Dynamic-2.7bpw) | 2.72 | 299 GiB | single Mac with generous headroom / smaller boxes |
+| [Q6 teacher (two-box)](https://huggingface.co/avlp12/Inkling-975B-Alis-MLX-Dynamic-6.6bpw) | 6.60 | 728 GiB | maximum fidelity, 2 × 512 GB pipeline serving |
 ---