Instructions to use TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4")
model = AutoModelForCausalLM.from_pretrained("TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4

SGLang

How to use TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4 with Docker Model Runner:
```
docker model run hf.co/TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4
```

Behemoth-R1-V2 ModelOpt NVFP4

NVFP4 quantized version of TheDrummer/Behemoth-R1-123B-v2 using NVIDIA Model Optimizer.

Quantization Details

Property	Value
Original Model	TheDrummer/Behemoth-R1-123B-v2
Quantization	NVFP4 (FP4 weights, FP16 activations)
Method	NVIDIA ModelOpt PTQ
Calibration Samples	512
Max Sequence Length	4096

Hardware Requirements

Optimal: NVIDIA Blackwell GPUs (B100, B200, RTX PRO 6000 Blackwell)
Compatible: Hopper/Ampere (will use weight-only mode)

Usage with vLLM

from vllm import LLM, SamplingParams

llm = LLM(
    model="TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4",
    quantization="modelopt",
    trust_remote_code=True,
)

sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=512)
outputs = llm.generate(["Write a story about..."], sampling_params)
print(outputs[0].outputs[0].text)

Chat Template

Uses Mistral v7 (Non-Tekken) format. See the original model card for usage details.

Credits

Original Model: TheDrummer
Quantization: TheHouseOfTheDude
Quantization Framework: NVIDIA ModelOpt

Downloads last month: 34

Safetensors

Model size

62B params

Tensor type

BF16

F8_E4M3

Model tree for TheHouseOfTheDude/Behemoth-R1-V2_ModelOpt-NVFP4

Base model

mistralai/Mistral-Large-Instruct-2411

Finetuned

TheDrummer/Behemoth-R1-123B-v2

Quantized

(15)

this model