Instructions to use tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic with Transformers:

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

pipe = pipeline("text-generation", model="tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic")
model = AutoModelForCausalLM.from_pretrained("tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic")
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 Settings

vLLM

How to use tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic

SGLang

How to use tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic 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 "tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic" \
    --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": "tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic",
		"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 "tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic" \
        --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": "tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic
```

Behemoth-R1-123B-v2-FP8-Dynamic / README.md

Irving Cabello

Add model card

de70ea5 verified 2 months ago

preview code

raw

history blame contribute delete

1.8 kB

	---
	tags:
	- fp8
	- quantized
	- mistral
	- roleplay
	- creative-writing
	- reasoning
	base_model: TheDrummer/Behemoth-R1-123B-v2
	library_name: transformers
	pipeline_tag: text-generation
	license: apache-2.0
	---

	# Behemoth-R1-123B-v2 FP8 Dynamic

	FP8 Dynamic quantization of [TheDrummer/Behemoth-R1-123B-v2](https://huggingface.co/TheDrummer/Behemoth-R1-123B-v2) using llmcompressor.

	## Model Details

	- Base Model: TheDrummer/Behemoth-R1-123B-v2 (Mistral Large 2411 finetune)
	- Quantization: FP8 Dynamic (W8A8) via llmcompressor
	- Scheme: FP8_DYNAMIC, lm_head excluded
	- Size: ~123 GB (vs 246 GB FP16)
	- Format: SafeTensors with compressed-tensors metadata

	## Usage with vLLM

	```bash
	python3 -m vllm.entrypoints.openai.api_server \
	--model Irvollo/Behemoth-R1-123B-v2-FP8-Dynamic \
	--quantization compressed-tensors \
	--dtype bfloat16 \
	--max-model-len 32768 \
	--gpu-memory-utilization 0.95 \
	--enable-prefix-caching \
	--trust-remote-code
	```

	## Reasoning / Thinking

	Supports native reasoning via `<think>` tag prefill:

	```json
	{
	"messages": [
	{"role": "user", "content": "Your question"},
	{"role": "assistant", "content": "<think>\n"}
	],
	"continue_final_message": true,
	"add_generation_prompt": false
	}
	```

	## Hardware Requirements

	- Single GPU: H200 NVL (141 GB) — tight with ~18 GB KV cache
	- Recommended: 2x A100 80GB or H100 for comfortable KV headroom

	## Quantization Details

	- Quantized on 2x NVIDIA B200 (358 GB VRAM)
	- Calibration: 616 linear layers in <1 second
	- Total pipeline: ~11 minutes
	- Tool: [llmcompressor](https://github.com/vllm-project/llm-compressor)

	## Credits

	- Original model by [TheDrummer](https://huggingface.co/TheDrummer)
	- FP8 quantization by [Irvollo](https://huggingface.co/Irvollo)