Instructions to use cbarkinozer/Reflex-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use cbarkinozer/Reflex-1 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 cbarkinozer/Reflex-1:Q8_0
# Run inference directly in the terminal:
llama cli -hf cbarkinozer/Reflex-1:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cbarkinozer/Reflex-1:Q8_0
# Run inference directly in the terminal:
llama cli -hf cbarkinozer/Reflex-1:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf cbarkinozer/Reflex-1:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf cbarkinozer/Reflex-1:Q8_0

Use Docker

docker model run hf.co/cbarkinozer/Reflex-1:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use cbarkinozer/Reflex-1 with Ollama:
```
ollama run hf.co/cbarkinozer/Reflex-1:Q8_0
```
Unsloth Desktop

How to use cbarkinozer/Reflex-1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cbarkinozer/Reflex-1:Q8_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": "cbarkinozer/Reflex-1:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use cbarkinozer/Reflex-1 with Docker Model Runner:
```
docker model run hf.co/cbarkinozer/Reflex-1:Q8_0
```

Lemonade

How to use cbarkinozer/Reflex-1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cbarkinozer/Reflex-1:Q8_0

Run and chat with the model

lemonade run user.Reflex-1-Q8_0

List all available models

lemonade list

Hermes Agent

How to use cbarkinozer/Reflex-1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cbarkinozer/Reflex-1:Q8_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 cbarkinozer/Reflex-1:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use cbarkinozer/Reflex-1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cbarkinozer/Reflex-1:Q8_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 "cbarkinozer/Reflex-1:Q8_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"

Reflex-1

File size: 1,034 Bytes

{
  "points": [
    {
      "id": "run-01",
      "label": "Reflex-1",
      "accuracy": 91.11111111111111,
      "latency_s": 31.364144939161097,
      "sampled_pss_mib": 1090.6455078125
    },
    {
      "id": "qwen-legacy-cached-fresh180",
      "label": "Base Qwen, cached app router",
      "accuracy": 54.44444444444444,
      "latency_s": 35.395459384916684,
      "sampled_pss_mib": 854.8271484375
    }
  ],
  "observed_frontiers": {
    "latency_s": [
      "run-01"
    ],
    "sampled_pss_mib": [
      "run-01",
      "qwen-legacy-cached-fresh180"
    ]
  },
  "input_sha256": "9928dd52c5b4946850e58502e014eefef54ff63aa2047f99283b167e3351a37a",
  "generator": "tools/plot_a32_efficiency.py",
  "matplotlib_version": "3.9.4",
  "definition": "Maximize accuracy and minimize the named cost; strict improvement in at least one objective.",
  "limitations": "Single runs; profile/policy and starting temperature differ. Sampled PSS is not in-flight peak memory. No measured energy or cross-model Decision Index frontier."
}