Instructions to use mlx-community/Inkling-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Inkling-mlx-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("mlx-community/Inkling-mlx-4bit")
config = load_config("mlx-community/Inkling-mlx-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

How to use mlx-community/Inkling-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 "mlx-community/Inkling-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": "mlx-community/Inkling-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use mlx-community/Inkling-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 "mlx-community/Inkling-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 mlx-community/Inkling-mlx-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/Inkling-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 "mlx-community/Inkling-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 "mlx-community/Inkling-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"

huckiyang commited on Jul 24

Commit

1f2ad6f

verified ·

1 Parent(s): 48d11ff

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ pipeline_tag: image-text-to-text
 An **MLX 4-bit** build of Thinking Machines' **Inkling** (975B-total / 41B-active MoE),
 quantized from the BF16 checkpoint for **Apple Silicon**. **Omni**: keeps the text decoder
-**plus the vision (HMLP) and audio (dMel) towers**. **Self-contained** — it bundles the loader
 package (`inkling_mlx/`), so it runs with just `mlx` + `mlx-lm` + `transformers`.
 The higher-fidelity sibling of [`mlx-community/Inkling-mlx-2bit`](https://huggingface.co/mlx-community/Inkling-mlx-2bit):
@@ -19,7 +19,7 @@ The higher-fidelity sibling of [`mlx-community/Inkling-mlx-2bit`](https://huggin
 ## Quantization (recipe: `experts_only`)
 - **4-bit** affine group quantization (group size 64) on the **routed experts** and the
-  **vision / audio matmuls** — the bulk of the weights.
 - **Kept in bf16 (protected):** attention, token / output embeddings, RMSNorms, the router
   gate, the per-layer short-convolutions, and the relative-position bias.
@@ -40,7 +40,7 @@ print(tok.decode(greedy_generate(model, config, ids, max_new_tokens=64)))
 ## Running on a single Mac with SSD expert-offload
-At ~548 GB this doesn't fit resident on one Mac — but an MoE only fires **6 of 256** experts
 per token. So keep the always-needed weights in RAM (attention, shared experts, embeddings,
 norms, router, vision / audio towers) and **page the routed experts from SSD on demand**,
 letting the OS page cache hold the hot ones. This runs the omni build on a single Mac Studio.

 An **MLX 4-bit** build of Thinking Machines' **Inkling** (975B-total / 41B-active MoE),
 quantized from the BF16 checkpoint for **Apple Silicon**. **Omni**: keeps the text decoder
+**plus the vision (HMLP) and audio (dMel) towers**. **Self-contained**. This bundles the loader
 package (`inkling_mlx/`), so it runs with just `mlx` + `mlx-lm` + `transformers`.
 The higher-fidelity sibling of [`mlx-community/Inkling-mlx-2bit`](https://huggingface.co/mlx-community/Inkling-mlx-2bit):
 ## Quantization (recipe: `experts_only`)
 - **4-bit** affine group quantization (group size 64) on the **routed experts** and the
+  **vision / audio matmuls** this is the bulk of the weights.
 - **Kept in bf16 (protected):** attention, token / output embeddings, RMSNorms, the router
   gate, the per-layer short-convolutions, and the relative-position bias.
 ## Running on a single Mac with SSD expert-offload
+At ~548 GB this doesn't fit resident on one Mac but an MoE only fires **6 of 256** experts
 per token. So keep the always-needed weights in RAM (attention, shared experts, embeddings,
 norms, router, vision / audio towers) and **page the routed experts from SSD on demand**,
 letting the OS page cache hold the hot ones. This runs the omni build on a single Mac Studio.