---
base_model: meta-llama/Llama-2-70b-hf
language:
- en
license: llama2
pipeline_tag: text-generation
tags:
- kronq
- quantization
- group-quantization
- int4
---

# Llama-2-70b — KronQ W4A16 g128 (packed int4)

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

[Llama-2-70b](https://huggingface.co/meta-llama/Llama-2-70b-hf) quantized to **4-bit weights / 16-bit activations**, **group size 128**, with **KronQ** (Kronecker-factored Hessian quantization). Packed int4 (~35 GB); fused dequant + BiIP CUDA kernel with per-group scales.

## Results (WikiText-2, seqlen 2048)

**Perplexity:** **3.380**

**Zero-shot accuracy:**

| PIQA | ARC-E | ARC-C | HellaSwag | WinoGrande | BoolQ | OBQA | Average |
|---|---|---|---|---|---|---|---|
| 82.70 | 79.21 | 56.23 | 84.05 | 79.79 | 84.95 | 48.40 | **73.62** |

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

## Usage

```bash
python eval_pretrained.py meta-llama/Llama-2-70b-hf donghyunli/Llama-2-70b-KronQ-W4A16-g128 --ppl --zs --distribute
```
(70B: `--distribute` spreads across GPUs.)

## Recipe

Group-128 asymmetric W4, weight-only, `--alpha 0.25`, `--act_order`, BiIP, raw H_G.

## License

Derivative of Llama-2-70b — [llama2 license](https://ai.meta.com/llama/license/).