Instructions to use deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use deadbydawn101/RavenX-Trade-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deadbydawn101/RavenX-Trade-8B-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": "deadbydawn101/RavenX-Trade-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M

Ollama
How to use deadbydawn101/RavenX-Trade-8B-GGUF with Ollama:
```
ollama run hf.co/deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M
```

Unsloth Studio

How to use deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for deadbydawn101/RavenX-Trade-8B-GGUF to start chatting

How to use deadbydawn101/RavenX-Trade-8B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deadbydawn101/RavenX-Trade-8B-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": "deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use deadbydawn101/RavenX-Trade-8B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deadbydawn101/RavenX-Trade-8B-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 "deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M
```

Lemonade

How to use deadbydawn101/RavenX-Trade-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.RavenX-Trade-8B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-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 deadbydawn101/RavenX-Trade-8B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

deadbydawn101 commited on May 30

Commit

cd527f3

verified ·

1 Parent(s): 6a71717

v1.1: Model card — 318K examples, MAP protocol, 128K context

Browse files

Files changed (1) hide show

README.md +40 -18

README.md CHANGED Viewed

@@ -10,6 +10,7 @@ tags:
   - hedge-fund
   - 128k-context
   - gguf
   - ravenx
   - map-protocol
 language:
@@ -17,23 +18,41 @@ language:
 pipeline_tag: text-generation
 ---
-# RavenX-Trade Qwen3-8B v1.1 — Autonomous Trading Intelligence Model 128K (GGUF)
-> **GGUF** · Ollama / llama.cpp / LM Studio · 128K context · 4-step MAP protocol · 318K training examples
-This is the GGUF version of [`RavenX-Trade-8B-MAP-128k-mlx-4bit`](https://huggingface.co/deadbydawn101/RavenX-Trade-8B-MAP-128k-mlx-4bit).
-> 🍎 **Looking for MLX?** → [RavenX-Trade-8B-MAP-128k-mlx-4bit](https://huggingface.co/deadbydawn101/RavenX-Trade-8B-MAP-128k-mlx-4bit)
-**Built by [@DeadByDawn101](https://github.com/DeadByDawn101) (RavenX LLC)**
-## Quick Start
 ```bash
 ollama run hf.co/deadbydawn101/RavenX-Trade-8B-GGUF:ravenx-trade-v1.1-128k-Q8_0
 ```
-## Example Output (v1.1 — 4-Step MAP)
 ```
 MAP STEP 1: MARKET
@@ -61,14 +80,7 @@ MAP STEP 4: TRADE
 - Position Size: 2.5% of portfolio
 ```
-## Available Quantizations
-| Filename | Quant | Use Case |
-|----------|-------|----------|
-| `ravenx-trade-v1.1-128k-Q4_K_M.gguf` | Q4_K_M | Fast inference, lower memory |
-| `ravenx-trade-v1.1-128k-Q5_K_M.gguf` | Q5_K_M | Balanced quality/speed |
-| `ravenx-trade-v1.1-128k-Q8_0.gguf` | Q8_0 | Best quality |
-| `ravenx-trade-v1.1-128k-f16.gguf` | F16 | Full precision |
 ## Model Details
@@ -76,12 +88,22 @@ MAP STEP 4: TRADE
 |-----------|-------|
 | **Architecture** | Qwen3-8B |
 | **Base** | Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 |
-| **Context** | 128K (YaRN rope scaling) |
-| **Training Data** | 318,675 examples |
-| **Datasets** | 21 HuggingFace + 15 GitHub repos |
 | **Method** | MLX LoRA (rank 32, 8 layers, 1e-5 LR, 2000 iters) |
 | **Hardware** | Apple M1 Max 64GB |
 ## Source Code
 **[github.com/DeadByDawn101/RavenX-Trade](https://github.com/DeadByDawn101/RavenX-Trade)**

   - hedge-fund
   - 128k-context
   - gguf
+  - ollama
   - ravenx
   - map-protocol
 language:
 pipeline_tag: text-generation
 ---
+# 🐦‍⬛ RavenX-Trade 8B v1.1 — GGUF (Ollama / llama.cpp / LM Studio)
+> **GGUF** · 128K context · 4-step MAP protocol · 318K training examples
+**Qwen3-8B fine-tuned for autonomous trading analysis.** GGUF quantizations for Ollama, llama.cpp, and LM Studio.
+> 🍎 **MLX (Apple Silicon):** [RavenX-Trade-8B-MAP-128k-mlx-4bit](https://huggingface.co/deadbydawn101/RavenX-Trade-8B-MAP-128k-mlx-4bit)
+>
+> 🛡️ **Security model:** [RavenX-Sec-8B-GGUF](https://huggingface.co/deadbydawn101/RavenX-Sec-8B-GGUF)
+**Built by [@DeadByDawn101](https://github.com/DeadByDawn101) · RavenX LLC**
+---
+## Quick Start (Ollama)
 ```bash
+# Run directly from HuggingFace — no push needed
 ollama run hf.co/deadbydawn101/RavenX-Trade-8B-GGUF:ravenx-trade-v1.1-128k-Q8_0
 ```
+---
+## Available Quantizations
+| File | Quant | Size | Use Case |
+|------|-------|------|----------|
+| `ravenx-trade-v1.1-128k-f16.gguf` | F16 | ~16 GB | Full precision, maximum quality |
+| `ravenx-trade-v1.1-128k-Q8_0.gguf` | Q8_0 | ~8.5 GB | Best quality quantized |
+| `ravenx-trade-v1.1-128k-Q5_K_M.gguf` | Q5_K_M | ~5.7 GB | Balanced quality/speed |
+| `ravenx-trade-v1.1-128k-Q4_K_M.gguf` | Q4_K_M | ~4.9 GB | Fast inference, lower memory |
+---
+## Example Output (4-Step MAP Protocol)
 ```
 MAP STEP 1: MARKET
 - Position Size: 2.5% of portfolio
 ```
+---
 ## Model Details
 |-----------|-------|
 | **Architecture** | Qwen3-8B |
 | **Base** | Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 |
+| **Context** | 128K (YaRN rope scaling, factor 4.0) |
+| **Training Data** | 318,675 examples (21 datasets + 15 repos) |
 | **Method** | MLX LoRA (rank 32, 8 layers, 1e-5 LR, 2000 iters) |
 | **Hardware** | Apple M1 Max 64GB |
+---
+## The RavenX Model Family
+| Model | Domain | Protocol | Training Data |
+|-------|--------|----------|--------------|
+| [**RavenX-Sec v4.0**](https://huggingface.co/deadbydawn101/RavenX-Sec-8B-GGUF) | Security | 6-step RATH | 610K examples |
+| [**RavenX-Trade v1.1**](https://huggingface.co/deadbydawn101/RavenX-Trade-8B-GGUF) | Trading | 4-step MAP | 318K examples |
+---
 ## Source Code
 **[github.com/DeadByDawn101/RavenX-Trade](https://github.com/DeadByDawn101/RavenX-Trade)**