Instructions to use txgsync/Maple-Preview-BF16-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use txgsync/Maple-Preview-BF16-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("txgsync/Maple-Preview-BF16-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 txgsync/Maple-Preview-BF16-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 "txgsync/Maple-Preview-BF16-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": "txgsync/Maple-Preview-BF16-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use txgsync/Maple-Preview-BF16-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 "txgsync/Maple-Preview-BF16-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "txgsync/Maple-Preview-BF16-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "txgsync/Maple-Preview-BF16-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use txgsync/Maple-Preview-BF16-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 "txgsync/Maple-Preview-BF16-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 txgsync/Maple-Preview-BF16-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use txgsync/Maple-Preview-BF16-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 "txgsync/Maple-Preview-BF16-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 "txgsync/Maple-Preview-BF16-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"

txgsync commited on 5 days ago

Commit

860fea7

verified ·

1 Parent(s): 55e5d69

Describe BF16 MLX conversion and oMLX loading

Browse files

Files changed (1) hide show

README.md +26 -7

README.md CHANGED Viewed

@@ -1,16 +1,35 @@
 ---
 license: mit
 language: en
-library_name: transformers
 pipeline_tag: text-generation
 tags:
-  - causal-lm
-  - mixture-of-experts
-  - reasoning
-  - ternary
-  - custom-code
 ---
 # Maple-Preview
 **DeepGrove · 2026**
@@ -31,7 +50,7 @@ Today we introduce Maple-Preview, an open-source 20B-A1B ternary-weight reasonin
 ## Architecture
-Maple-Preview is a 20B-A1B reasoning model designed from the start for efficient on-device inference. It utilizes a 24-layer, 256-expert (8 active) configuration with 3:1 SWA-512:GA attention.
 ## Evaluation

 ---
 license: mit
 language: en
+library_name: mlx
 pipeline_tag: text-generation
+base_model: deepgrove/maple-preview
 tags:
+- mlx
+- causal-lm
+- mixture-of-experts
+- reasoning
+- custom-code
+- bf16
 ---
+# Maple Preview — BF16 MLX conversion
+This repository contains the full-precision BF16 MLX conversion of [`deepgrove/maple-preview`](https://huggingface.co/deepgrove/maple-preview).
+## This MLX upload
+- Approximately 38 GB on disk.
+- Converted directly from the original Hugging Face BF16 safetensors; no 2-bit checkpoint was dequantized.
+- Includes the official Maple model implementation as `maple.py`.
+- Requires custom-code loading (`trust_remote_code=True`). In oMLX, enable **Trust Remote Code** for this model.
+This is an MLX conversion for local inference on Apple Silicon. Please follow the base model's MIT license and usage terms.
+---
+## Base model description
 # Maple-Preview
 **DeepGrove · 2026**
 ## Architecture
+Maple-Preview is a 20B-A1B reasoning model designed from the start for efficient on-device inference. It utilizes a 24-layer, 256-expert (8 active) configuration with 3:1 SWA-512:GA attention.
 ## Evaluation