Instructions to use TheDrummer/Behemoth-123B-v1.2-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 TheDrummer/Behemoth-123B-v1.2-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 TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheDrummer/Behemoth-123B-v1.2-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 TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheDrummer/Behemoth-123B-v1.2-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 TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheDrummer/Behemoth-123B-v1.2-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 TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use TheDrummer/Behemoth-123B-v1.2-GGUF with Ollama:
```
ollama run hf.co/TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M
```
Unsloth Desktop

How to use TheDrummer/Behemoth-123B-v1.2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheDrummer/Behemoth-123B-v1.2-GGUF: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": "TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TheDrummer/Behemoth-123B-v1.2-GGUF with Docker Model Runner:
```
docker model run hf.co/TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M
```

Lemonade

How to use TheDrummer/Behemoth-123B-v1.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Behemoth-123B-v1.2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use TheDrummer/Behemoth-123B-v1.2-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 TheDrummer/Behemoth-123B-v1.2-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 TheDrummer/Behemoth-123B-v1.2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TheDrummer/Behemoth-123B-v1.2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheDrummer/Behemoth-123B-v1.2-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 "TheDrummer/Behemoth-123B-v1.2-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"

Nbv9pQ88Xb

2500+ members strong 💪 Now with more channels! A hub for users and makers alike!

BeaverAI proudly presents...

Behemoth 123B v1.2 🦣 - The Definitive Edition

When you spend your whole life living under a dome, even the idea of an ocean seems impossible to imagine.

Description

v1.2 is a go! Crazy to say but I believe it's better than your 2* versions in every way. Great work as always

Switched back to 1.1 after using 1.2 and yeah the difference is obvious. I prefer the prose of 1.2 better. It's more varied.

Yeah it is truly an upgrade in every sense if the word if you ask me

100%. 1.2 is my favourite Behemoth iteration. It's crazy to me just how different it feels from the 2.x series.

It's my favorite model period. The vast majority of all responses are fresh. Every chat feels more natural too.

I just absolutely love what it does to my characters. I haven't seen them say the things 1.2 has said before, but it feels so natural

The prose in 1.2 is 🤌🤌🤌

Gonna go ahead and give a 👍 for releasing it. I like this version a lot. Better than 2.2 imo. I haven't seen any impersonation. The rp stuck to the card and was very deep and creative. Less predictable than 1.1, but not flat out nuts like 2.2.

So far, I have to concur. I'm impressed with 1.2

Arsenal (Supported Chat Templates)

Metharme (Pygmalion in ST)
- Creative, unhinged, unique

Favorite RP Format

*action* Dialogue *thoughts* Dialogue *narration* in 1st person PoV

Favorite Card

Audrey by thecooler

What's Next?

For Largestral 2407??? That would mean AI winter!

Special Thanks

Thank you to each and everyone who donated in Ko-Fi to make our venture a little bit easier.
- KinjiHakari777, Dr. Fjut, Kistara, Pseudo, AlexTheVP, Dakkidaze, EvarinSharath'fe, ONTHEREDTEAM, F, Mariana, Garg, Silva, Grozi, Phaelon, joe

BEHEMOTH SUPREMACY

Downloads last month: 274

GGUF

Model size

123B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

TheDrummer
/

Behemoth-123B-v1.2-GGUF

Join our Discord! https://discord.gg/Nbv9pQ88Xb

2500+ members strong 💪 Now with more channels! A hub for users and makers alike!

Behemoth 123B v1.2 🦣 - The Definitive Edition

Description

Links

Arsenal (Supported Chat Templates)

Favorite RP Format

Favorite Card

What's Next?

Special Thanks

BEHEMOTH SUPREMACY