Instructions to use BeaverAI/Behemoth-R1-123B-v2a-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BeaverAI/Behemoth-R1-123B-v2a-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BeaverAI/Behemoth-R1-123B-v2a-GGUF",
	filename="Behemoth-R1-123B-v2a-Q3_K_M-00001-of-00002.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use BeaverAI/Behemoth-R1-123B-v2a-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BeaverAI/Behemoth-R1-123B-v2a-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 BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BeaverAI/Behemoth-R1-123B-v2a-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 BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M

Use Docker

docker model run hf.co/BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use BeaverAI/Behemoth-R1-123B-v2a-GGUF with Ollama:
```
ollama run hf.co/BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M
```

Unsloth Studio

How to use BeaverAI/Behemoth-R1-123B-v2a-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 BeaverAI/Behemoth-R1-123B-v2a-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 BeaverAI/Behemoth-R1-123B-v2a-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BeaverAI/Behemoth-R1-123B-v2a-GGUF to start chatting

Docker Model Runner
How to use BeaverAI/Behemoth-R1-123B-v2a-GGUF with Docker Model Runner:
```
docker model run hf.co/BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M
```

Lemonade

How to use BeaverAI/Behemoth-R1-123B-v2a-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BeaverAI/Behemoth-R1-123B-v2a-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Behemoth-R1-123B-v2a-GGUF-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Mistral (Non-Tekken), i.e., Mistral v3 + [SYSTEM_PROMPT]

Looks like <think> doesn't need to be prefilled. You can opt out of reasoning - it's just as good, maybe even better.

No toxic data so you may want to prefill / guide reasoning when dealing with heavy themes (unless your prompt is sufficiently instructed/gaslit to be evil).

Alternatively, since <think> is not a special token, you can influence reasoning by phrasing it like <evil_think>, <creative_think>, or <spicy_think>, etc. It's smart enough to close it properly.

Yes, this is how much I want to avoid tuning MoEs.

Downloads last month: 9

GGUF

Model size

123B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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