---
license: other
base_model: JetBrains/Mellum2.1-12B-A2.5B-Thinking
base_model_relation: quantized
library_name: transformers
pipeline_tag: text-generation
tags:
- fp8
- compressed-tensors
- vllm
- quantized
quantized_by: liodon-ai
---

# Mellum2.1-12B-A2.5B-Thinking — FP8 (dynamic)

FP8 quantization of [JetBrains/Mellum2.1-12B-A2.5B-Thinking](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking), published by [Liodon AI](https://huggingface.co/liodon-ai).

Quantized with [llm-compressor](https://github.com/vllm-project/llm-compressor) using the
`FP8_DYNAMIC` scheme: weights are cast to FP8 (E4M3) per-channel ahead of time, activations are
quantized to FP8 dynamically per-token at inference time. No calibration dataset is needed for this
scheme, so the quantized weights are numerically just a direct cast of the original — no calibration-set
bias to worry about. `lm_head` is left unquantized (standard practice — negligible size, disproportionate
quality impact if quantized).

Original size: 24.3 GB → Quantized: 12.6 GB.

## Quick Start

**vLLM**
```bash
vllm serve liodon-ai/Mellum2.1-12B-A2.5B-Thinking-FP8
```

**Text Generation Inference (TGI)**
```bash
docker run --gpus all -p 8080:80 ghcr.io/huggingface/text-generation-inference \
    --model-id liodon-ai/Mellum2.1-12B-A2.5B-Thinking-FP8
```

**SGLang**
```bash
python -m sglang.launch_server --model-path liodon-ai/Mellum2.1-12B-A2.5B-Thinking-FP8
```

FP8 execution requires an NVIDIA GPU with compute capability ≥ 8.9 (Ada/Hopper/Blackwell — RTX 40-series,
L4/L40S, H100/H200, B100/B200/GB10). On older GPUs, vLLM/TGI will dequantize to run, which loses the
speed/memory benefit.

## Source

- **Model**: [JetBrains/Mellum2.1-12B-A2.5B-Thinking](https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking)
- **License**: other

## Citation

```bibtex
@misc{liodonai_mellum2_1_12b_a2_5b_thinking_fp8,
  title        = {Mellum2.1-12B-A2.5B-Thinking — FP8},
  author       = {{Liodon AI}},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/liodon-ai/Mellum2.1-12B-A2.5B-Thinking-FP8}},
  note         = {FP8 (dynamic) quantization of JetBrains/Mellum2.1-12B-A2.5B-Thinking}
}
```

---
*Quantized by [Liodon AI](https://huggingface.co/liodon-ai)*