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

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

FP8 Dynamic quantization of 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

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:

{
  "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

Credits

Original model by TheDrummer
FP8 quantization by Irvollo

Downloads last month: 6

Safetensors

Model size

123B params

Tensor type

BF16

F8_E4M3

Model tree for tacodevs/Behemoth-R1-123B-v2-FP8-Dynamic

Base model

mistralai/Mistral-Large-Instruct-2411

Finetuned

TheDrummer/Behemoth-R1-123B-v2

Quantized

(14)

this model