Instructions to use patriotmemory-ai/PMA-1.0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use patriotmemory-ai/PMA-1.0-GGUF 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 patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

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 patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

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 patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

Use Docker

docker model run hf.co/patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use patriotmemory-ai/PMA-1.0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "patriotmemory-ai/PMA-1.0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patriotmemory-ai/PMA-1.0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

Ollama
How to use patriotmemory-ai/PMA-1.0-GGUF with Ollama:
```
ollama run hf.co/patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M
```

Unsloth Studio

How to use patriotmemory-ai/PMA-1.0-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for patriotmemory-ai/PMA-1.0-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for patriotmemory-ai/PMA-1.0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for patriotmemory-ai/PMA-1.0-GGUF to start chatting

How to use patriotmemory-ai/PMA-1.0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use patriotmemory-ai/PMA-1.0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

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 "patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M" \
  --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"

Docker Model Runner
How to use patriotmemory-ai/PMA-1.0-GGUF with Docker Model Runner:
```
docker model run hf.co/patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M
```

Lemonade

How to use patriotmemory-ai/PMA-1.0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.PMA-1.0-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use patriotmemory-ai/PMA-1.0-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

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 patriotmemory-ai/PMA-1.0-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Patriot Memory AI Model

Welcome to the official repository for the Patriot Memory AI Model. Developed by Patriot Memory (patriotmemory.com), this lightweight, fine-tuned language model is optimized for hardware domain knowledge, customer support, compatibility checks, and function/tool calling.

Model Overview

PMA-1.0 is a lightweight language model based on the MiniMind architecture, designed for fast inference and efficient deployment.

This model serve as an intelligent representative for Patriot Memory and its premium gaming brand, Viper Gaming. It provides accurate information regarding:

DDR4 & DDR5 RAM: Specifications, XMP 3.0 / EXPO profile support, dual-channel setups, and overclocking guidance.
PCIe & SATA SSDs: Gen3/Gen4/Gen5 compatibility, read/write performance specifications, and installation troubleshooting.
Gaming Peripherals & Storage: USB drives, flash cards, and Viper Gaming gear.
Tool / Function Calling: Seamless integration with backend APIs (e.g., checking warranty status, looking up technical specs via S/N).

Model Information

Property	Specification
Model Type	Causal Language Model (Dense Decoder-Only)
Total Parameters	~63.9 Million (0.064B)
Context Length	32,768 tokens (32K)
Hidden Size (Embedding)	768
Intermediate Size (FFN)	2,432
Attention Heads	8 Query heads (4 KV heads)
Num Layers	8 Transformer blocks
Primary Language	Traditional Chinese (zh-TW) / English (en)

Quickstart Guide

Installation Ensure you have transformers and torch installed:

pip install transformers torch

Inference Code

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "patriotmemory-ai/pma-1.0"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    dtype="auto",
    device_map="auto"
)

prompt = "博帝的 Viper Venom DDR5 記憶體支援 XMP 3.0 嗎?"
messages = [
    {"role": "system", "content": "你是 Patriot Memory（博帝科技）的官方智能客服小幫手。"},
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
model_inputs.pop("token_type_ids", None)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)

input_len = model_inputs["input_ids"].shape[1]
generated_tokens = generated_ids[0][input_len:]

response = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(response)

Limitations & Responsible Use

PMA-1.0 is a probabilistic language model trained on statistical patterns. Please keep the following in mind when deploying or evaluating this model:

Generation Risks: The model may generate inaccurate, hallucinated, biased, or objectionable content. Outputs should always be independently verified—especially in high-stakes domain applications (e.g., medical, legal, or financial).
Preview Release: As an experimental preview, model behavior, outputs, and performance metrics may vary between updates and versions.
User Responsibility: Users and developers are responsible for implementing appropriate safety guardrails, evaluating outputs for their specific use cases, and ensuring compliance with applicable laws, regulations, and platform safety guidelines.

Official Links

Official Website: patriotmemory.com

Viper Gaming: viper.patriotmemory.com

Support & Warranty: patriotmemory.com/support

Model Inquiries & Feedback: danton.chu@patriotmemory.com hunter.wang@patriotmemory.com oda.chang@patriotmemory.com york.lin@patriotmemory.com

License

This model card and associated weights are released under the Apache 2.0 License.

Downloads last month: 501

GGUF

Model size

63.9M params

Architecture

qwen3

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit