---
base_model: meta-llama/Llama-2-13b-hf
language:
- en
license: llama2
pipeline_tag: text-generation
tags:
- kronq
- quantization
- group-quantization
- int2
---

# Llama-2-13b — KronQ W2A16 g128 (packed int2)

**Paper:** [arXiv:2607.07964](https://arxiv.org/abs/2607.07964) · **Code:** [GitHub](https://github.com/Intelligent-Computing-Lab-Panda/KronQ)

[Llama-2-13b](https://huggingface.co/meta-llama/Llama-2-13b-hf) quantized to **2-bit weights / 16-bit activations**, **group size 128**, with **KronQ** (Kronecker-factored Hessian quantization). Packed int2 (~4.0 GB); a fused dequant + bidirectional-incoherence (BiIP) CUDA kernel with per-group scales unpacks on the fly.

## Results (WikiText-2, seqlen 2048)

**Perplexity:** **6.508**

**Zero-shot accuracy:**

| PIQA | ARC-E | ARC-C | HellaSwag | WinoGrande | BoolQ | OBQA | Average |
|---|---|---|---|---|---|---|---|
| 72.58 | 68.86 | 38.14 | 63.88 | 65.98 | 66.02 | 36.80 | **58.89** |

(lm-evaluation-harness 0-shot; acc_norm for PIQA/HellaSwag/ARC, acc for WinoGrande/BoolQ.)

## Usage

```bash
python eval_pretrained.py meta-llama/Llama-2-13b-hf donghyunli/Llama-2-13b-KronQ-W2A16-g128 --ppl --zs
```

## Recipe

Group-128 asymmetric W2, weight-only (a_bits=16), `--alpha 0.25`, `--act_order`, BiIP, raw H_G. 128 WikiText-2 calibration sequences.

## License

Derivative of Llama-2-13b — [llama2 license](https://ai.meta.com/llama/license/).