# 1.58-bit quantization

A 1.58-bit quantized large language model developed by Microsoft, designed for efficient inference, offering IQ2_BN and IQ2_BN_R4 quantization versions

Falcon-E-3B-Instruct is an efficient language model based on a 1.58-bit architecture, optimized for edge devices, with excellent inference capabilities and low memory usage.

Falcon-E-1B-Instruct is an efficient language model based on a 1.58-bit architecture, optimized for edge devices with low memory footprint and high performance.

Falcon-E is a 1.58-bit quantized language model developed by TII, featuring a pure Transformer architecture designed for efficient inference

The first open-source, native 1-bit large language model developed by Microsoft Research, with a parameter scale of 2 billion, trained on a corpus of 4 trillion tokens.

The first open-source 2-billion-parameter native 1-bit large language model developed by Microsoft Research, trained on 4 trillion tokens, demonstrating that native 1-bit large language models can significantly improve computational efficiency while maintaining performance comparable to full-precision open-source models of the same scale.

An open-source native 1-bit large language model developed by Microsoft Research, with 2 billion parameters trained on a 4 trillion token corpus, significantly improving computational efficiency.

Falcon-E-1B-Base is an efficient 1.58-bit language model developed by TII, featuring a pure Transformer architecture and optimized for edge devices.

A GGUF format model converted from Meta-Llama-3-8B-Instruct and HF1BitLLM/Llama3-8B-1.58-100B-tokens models, suitable for llama.cpp inference

Large language model fine-tuned based on BitNet 1.58b architecture, with Llama-3-8B-Instruct as the base model, employing extreme quantization techniques

BitNet b1.58 is a large language model with 1.58-bit quantization. It reduces the computational resource requirements by lowering the weight precision while maintaining performance close to that of a full-precision model.

BitNet b1.58 is a 1-bit large language model with 3 billion parameters, trained on the RedPajama dataset for 100 billion tokens.