Irvollo/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