Instructions to use OpenMed/maple-preview-8bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMed/maple-preview-8bit-mlx 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("OpenMed/maple-preview-8bit-mlx")

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 OpenMed/maple-preview-8bit-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OpenMed/maple-preview-8bit-mlx"

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": "OpenMed/maple-preview-8bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use OpenMed/maple-preview-8bit-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OpenMed/maple-preview-8bit-mlx"

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 "OpenMed/maple-preview-8bit-mlx" \
  --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"

MLX LM

How to use OpenMed/maple-preview-8bit-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OpenMed/maple-preview-8bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OpenMed/maple-preview-8bit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OpenMed/maple-preview-8bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use OpenMed/maple-preview-8bit-mlx 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 "OpenMed/maple-preview-8bit-mlx"

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 OpenMed/maple-preview-8bit-mlx

Run Hermes

hermes

Maple Preview 8-bit MLX

Private OpenMed development export of deepgrove/maple-preview for MLX. It was converted from source revision ac1ddd79d2b5cb4406f5d2bebdf95406ce505a07 with 8-bit affine quantization and group size 128. The included openmed-maple-export.json records the pinned source and runtime-code revisions and conversion settings.

Validation status

On Apple Silicon, this export loaded and completed OpenMed's synthetic task contracts for PII span proposals, clinical entities, relations, concise reasoning, and grounded visible chat. These are development contract checks, not clinical-quality evidence. Direct-identifier recall, critical-leakage, source-parity, memory, thermal, and physical-device release gates remain.

OpenMed use

The OpenMedKit integration, prompt contracts, and native iOS scanning demo are documented in docs/maple-on-device.md. Structured outputs must pass OpenMed's span, label-vocabulary, relation, and grounding validators before they are shown or applied. Do not log prompts that may contain protected information.

Maple Preview is a research model with limited post-training. It is not a medical device and must not automatically trigger diagnosis, treatment, disclosure, or another consequential decision. Human review is required.

Attribution and license

This is a quantized derivative of DeepGrove's Maple Preview. The upstream model is licensed under MIT; see the upstream repository for its license and model card. OpenMed's SDK source is separately licensed under Apache-2.0.

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

BF16

U32

MLX

Hardware compatibility

8-bit

Model tree for OpenMed/maple-preview-8bit-mlx

Base model

deepgrove/maple-preview

Quantized

(8)

this model