Instructions to use Sawfwair/Inkling-Small-MLX-Mixed-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sawfwair/Inkling-Small-MLX-Mixed-2bit 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("Sawfwair/Inkling-Small-MLX-Mixed-2bit")
config = load_config("Sawfwair/Inkling-Small-MLX-Mixed-2bit")

# 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 Sawfwair/Inkling-Small-MLX-Mixed-2bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Sawfwair/Inkling-Small-MLX-Mixed-2bit"

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": "Sawfwair/Inkling-Small-MLX-Mixed-2bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use Sawfwair/Inkling-Small-MLX-Mixed-2bit 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 "Sawfwair/Inkling-Small-MLX-Mixed-2bit"

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 Sawfwair/Inkling-Small-MLX-Mixed-2bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Sawfwair/Inkling-Small-MLX-Mixed-2bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Sawfwair/Inkling-Small-MLX-Mixed-2bit"

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 "Sawfwair/Inkling-Small-MLX-Mixed-2bit" \
  --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"

Inkling-Small MLX mixed 2-bit

Mixed-precision MLX conversion of thinkingmachines/Inkling-Small at revision b2d4f225a02032c5d154bff748ab5a00c5ca26e4. The conversion uses MLX 0.32.0 and mlx-vlm 0.6.7. See conversion.json for the machine-readable provenance and artifact inventory.

Only the 256 routed experts in each sparse MoE layer use affine 2-bit, group-128 weights. Attention, embeddings, routers, shared experts, dense MLPs, normalization, vision, and audio weights remain at the released BF16 precision. This conservative split targets 128 GB unified-memory Macs while protecting the non-routed paths that blanket 2-bit quantization damaged.

Validation status

The conversion gate checks the affine 2-bit/group-128 routed-expert metadata, all 120 quantized expert projections, every shard, and representative BF16 and packed tensor shapes.

On 2026-07-31, a full CUDA load and greedy generation smoke with MLX 0.32.0 and mlx-vlm 0.6.7 used 84,530,593,368 bytes of active MLX memory and peaked at 84,766,898,240 bytes on an NVIDIA H200. The model correctly answered 2 + 2 with 4, the "all but 9" sheep question with 9, and produced a correct Swift isEven function. This proves CUDA loading and token quality for the generated artifact; Apple Silicon runtime validation is tracked separately by mere.run.

mlx-vlm 0.6.7 also required the compatibility shims in the conversion script for its Inkling config exports and CUDA mask fallback; the managed mere.run lane uses its own native Swift/MLX loader.

mere.run text chat --model text-chat-inkling-small --prompt "Who are you?"

Downloads last month: 406

Safetensors

Model size

26B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

2-bit

Model tree for Sawfwair/Inkling-Small-MLX-Mixed-2bit

Base model

thinkingmachines/Inkling-Small

Quantized

(43)

this model