Instructions to use fxiafx/firela-pa-pc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use fxiafx/firela-pa-pc 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 fxiafx/firela-pa-pc:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf fxiafx/firela-pa-pc:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fxiafx/firela-pa-pc:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf fxiafx/firela-pa-pc: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 fxiafx/firela-pa-pc:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf fxiafx/firela-pa-pc: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 fxiafx/firela-pa-pc:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fxiafx/firela-pa-pc:Q4_K_M

Use Docker

docker model run hf.co/fxiafx/firela-pa-pc:Q4_K_M

LM Studio
Jan
Ollama
How to use fxiafx/firela-pa-pc with Ollama:
```
ollama run hf.co/fxiafx/firela-pa-pc:Q4_K_M
```
Unsloth Desktop

How to use fxiafx/firela-pa-pc with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fxiafx/firela-pa-pc:Q4_K_M

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": "fxiafx/firela-pa-pc:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use fxiafx/firela-pa-pc with Docker Model Runner:
```
docker model run hf.co/fxiafx/firela-pa-pc:Q4_K_M
```

Lemonade

How to use fxiafx/firela-pa-pc with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fxiafx/firela-pa-pc:Q4_K_M

Run and chat with the model

lemonade run user.firela-pa-pc-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use fxiafx/firela-pa-pc with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fxiafx/firela-pa-pc: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 fxiafx/firela-pa-pc:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use fxiafx/firela-pa-pc with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fxiafx/firela-pa-pc: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 "fxiafx/firela-pa-pc: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"

firela-pa PC — 本地财务隐私路由器（GGUF + 一键安装）

firela-pa 的 PC 形态分发仓：Qwen3-1.7B 任务微调隐私路由模型（fmt-v1.1 五意图： tx 查账 / pf 资产全景 / mkt 行情 / l 本地闲聊 / c 涂黑上云），W8A8 板载同源权重的 GGUF 版（Q4_K_M 为默认分发档，Q8_0 为质量档——两者在 eval200 200 题上门禁逐题全同， G4 97%）。基座 Qwen3-1.7B（Apache-2.0），LoRA 合并权重可再分发。

一键安装（macOS / Linux / WSL2）

bash <(curl -fsSL https://huggingface.co/fxiafx/firela-pa-pc/resolve/main/install.sh)

自动完成：装/起 Ollama → 下载本仓应用与路由模型（sha256 校验）→ 注册 firela-router → 拉生成模型 qwen2.5:3b-instruct（非思考原生 ~1s；--no-gen 可跳过，可在 config 换 qwen3:4b 等思考模型——Ollama think 参数对库版 qwen3 模板不生效，慎用）→ 交互式生成 0600 配置（vlt / relay 凭证，回车可留空后补）→ Time Machine 排除 → firela-pa 命令 → 冒烟。

隐私边界：推理不出门——路由/闲聊生成全本地；查账走用户自己的 vlt 令牌；上云问句先经确定性涂黑（身份四类整段替换，详见应用仓设计文档）。

文件	用途
`pc-app.tar.gz`	编排器 + 涂黑器 + 评测/解析（纯 stdlib Python）
`router-merged-Q4_K_M.gguf`	路由模型默认档（1.1GB）
`router-merged-Q8_0.gguf`	路由模型质量档（1.9GB，可选）
`install.sh`	一键安装脚本

Downloads last month: 87

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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