Built with Llama. Balanced ternary quantization of meta-llama/Llama-3.1-8B at depth d=3 (27 levels per weight, 5.05 bits per weight). Distributed under the Llama 3.1 Community License Agreement and subject to Meta's Acceptable Use Policy.

Produced with the codec from "Balanced Ternary Post-Training Quantization for Large Language Models" (Stentzel, 2026). See Entrit/tritllm-codec for the codec source.

Quick load

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Entrit/Llama-3.1-8B-trit-uniform-d3")
tokenizer = AutoTokenizer.from_pretrained("Entrit/Llama-3.1-8B-trit-uniform-d3")

The weights are dequantized to FP16 for stock-transformers compatibility. The on-disk size is therefore the same as the FP16 source. The 5.05-bpw figure refers to the information content of the quantized matrices and is what matters for inference on hardware that consumes the packed trit format directly (see Entrit/tritllm-kernel).

Quantization details

Field	Value
Source model	`meta-llama/Llama-3.1-8B`
Depth	d=3 (27 levels)
Bits per weight	5.05
Group size	16
Scale codebook	27-entry log-spaced (scale_depth=3)
Method	Uniform PTQ
Quantized layers	all 2D linear matrices
Kept FP16	`lm_head`, token embeddings, all `*_norm` layers
Codec	tritllm v2

License and use

This is a research artifact. The underlying weights remain governed by the Llama 3.1 Community License Agreement; commercial use is restricted to the terms of that license. By using this model you agree to:

Comply with the Llama 3.1 Community License.
Comply with Meta's Acceptable Use Policy.
Display "Built with Llama" attribution if you redistribute or publicly demo derivatives of this model.

Citation

@article{stentzel2026ternaryptq,
  title  = {Balanced Ternary Post-Training Quantization for Large Language Models},
  author = {Stentzel, Eric},
  year   = 2026,
  note   = {Entrit Systems}
}

Reproducibility

bash

git clone https://huggingface.co/Entrit/tritllm-codec
cd tritllm-codec
python quantize_model_v2.py --model meta-llama/Llama-3.1-8B --configs uniform-d3 --out ./out