Instructions to use phantomic12/maple-preview-20b-q4nx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use phantomic12/maple-preview-20b-q4nx with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf phantomic12/maple-preview-20b-q4nx:TQ2_0
# Run inference directly in the terminal:
llama cli -hf phantomic12/maple-preview-20b-q4nx:TQ2_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf phantomic12/maple-preview-20b-q4nx:TQ2_0
# Run inference directly in the terminal:
llama cli -hf phantomic12/maple-preview-20b-q4nx:TQ2_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf phantomic12/maple-preview-20b-q4nx:TQ2_0
# Run inference directly in the terminal:
./llama-cli -hf phantomic12/maple-preview-20b-q4nx:TQ2_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf phantomic12/maple-preview-20b-q4nx:TQ2_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf phantomic12/maple-preview-20b-q4nx:TQ2_0

Use Docker

docker model run hf.co/phantomic12/maple-preview-20b-q4nx:TQ2_0

LM Studio
Jan
Ollama
How to use phantomic12/maple-preview-20b-q4nx with Ollama:
```
ollama run hf.co/phantomic12/maple-preview-20b-q4nx:TQ2_0
```
Unsloth Desktop

How to use phantomic12/maple-preview-20b-q4nx with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf phantomic12/maple-preview-20b-q4nx:TQ2_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "phantomic12/maple-preview-20b-q4nx:TQ2_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use phantomic12/maple-preview-20b-q4nx with Docker Model Runner:
```
docker model run hf.co/phantomic12/maple-preview-20b-q4nx:TQ2_0
```

Lemonade

How to use phantomic12/maple-preview-20b-q4nx with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull phantomic12/maple-preview-20b-q4nx:TQ2_0

Run and chat with the model

lemonade run user.maple-preview-20b-q4nx-TQ2_0

List all available models

lemonade list

Hermes Agent

How to use phantomic12/maple-preview-20b-q4nx with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf phantomic12/maple-preview-20b-q4nx:TQ2_0

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 phantomic12/maple-preview-20b-q4nx:TQ2_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use phantomic12/maple-preview-20b-q4nx with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf phantomic12/maple-preview-20b-q4nx:TQ2_0

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 "phantomic12/maple-preview-20b-q4nx:TQ2_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Maple-Preview 20B (Q4NX & TQ2_0 Quantized for FastFlowLM / AMD Ryzen AI NPU)

This repository contains the FastFlowLM Q4NX & TQ2_0 quantized weights of DeepGrove's Maple-Preview (20B-A1B ternary reasoning MoE model), optimized for high-speed inference on AMD Ryzen AI NPUs (XDNA 2 / Strix Point) and modern AVX2/FMA CPUs.

🚀 Model & Runtime Highlights

Base Architecture: 20B Total Parameters (~1B active per token, 256 experts with Top-8 routing).
Hybrid 3:1 Attention: 18 Sliding Window Attention layers (512-token span) + 6 Full Global Attention layers.
Native 128K Context Window: Full 131,072 token context support with $O(1)$ constant 18.9 MB SWA memory overhead.
Hardware NPU Acceleration: Achieves >185–202 tokens/second on AMD Ryzen AI 9 HX 370 NPU (/dev/accel/accel0).
OpenAI-Compatible REST Server: Native /v1/chat/completions and streaming <think> reasoning support.

📦 File Inventory

model.q4nx: FastFlowLM packed ternary/quantized weights for NPU & CPU runtime.
maple-preview-TQ2_0-head-Q4_K.gguf: GGUF format checkpoint for cross-runtime compatibility.
config.json: Architecture configuration and hyperparameter specifications.
tokenizer.json & tokenizer_config.json: Byte-level BPE tokenizer (151,936 vocabulary).
chat_template.jinja: Jinja chat template with reasoning toggle (<think> ... </think>).

🛠️ Quickstart with FastFlowLM

1. Clone Runtime & Setup

git clone https://github.com/phantomic12/maple-flm.git
cd maple-flm
bash install.sh

2. Download Weights via Hugging Face CLI (`hf`)

hf download phantomic12/maple-preview-20b-q4nx --local-dir models/maple-preview-20b

3. Run Inference on NPU

# Interactive Chat
bash scripts/chat_maple.sh

# Launch OpenAI-Compatible REST Server
bash scripts/serve_maple.sh

# Run Hardware Benchmarks
bash scripts/benchmark_npu.sh

📊 Performance Benchmarks (AMD Ryzen AI 9 HX 370 NPU)

Context Length	Prefill Speed	Decode Speed	Memory Footprint
4K Context	199.6 tok/s	190.2 tok/s	~5.6 GB RAM
32K Context	200.1 tok/s	187.9 tok/s	~5.9 GB RAM
128K Context	202.6 tok/s	185.6 tok/s	~7.1 GB RAM
1M Context (Extreme)	193.2 tok/s	175.4 tok/s	~18.4 GB RAM

📜 Citation & Credits

Original Model: deepgrove/maple-preview
FastFlowLM Runtime: ROCm/FastFlowLM
Port & Optimizations: phantomic12/maple-flm

Downloads last month: 61

GGUF

Model size

20B params

Architecture

maple

Hardware compatibility

2-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for phantomic12/maple-preview-20b-q4nx

Base model

deepgrove/maple-preview

Quantized

(12)

this model

Maple-Preview 20B (Q4NX & TQ2_0 Quantized for FastFlowLM / AMD Ryzen AI NPU)

🚀 Model & Runtime Highlights

📦 File Inventory

🛠️ Quickstart with FastFlowLM

1. Clone Runtime & Setup

2. Download Weights via Hugging Face CLI (hf)

3. Run Inference on NPU

📊 Performance Benchmarks (AMD Ryzen AI 9 HX 370 NPU)

📜 Citation & Credits

Model tree for phantomic12/maple-preview-20b-q4nx

2. Download Weights via Hugging Face CLI (`hf`)