low-bit

Here are 13 public repositories matching this topic...

intel / neural-speed

An innovative library for efficient LLM inference via low-bit quantization

Updated Aug 30, 2024
C++

Tylogi / MFQ

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the hardware you already own.

Updated Sep 24, 2026
C++

fdbtrs / QuantFace

Star

QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization

face biometrics face-recognition quantization low-bit biometrics-facialrecognition

Updated Jun 26, 2022
Python

pyjhzwh / low-bit-quant-admm

Star

admm for cnn layerwise weight low bit quantization

python neural-network admm quantization low-bit

Updated Sep 25, 2019
Python

yanfeiwong / adafactor-8bit

Star

Memory-efficient PyTorch optimizers with Adaptive Log-Space quantization, fused CUDA kernels, and Adafactor, CAME, APOLLO support.

machine-learning deep-learning cuda pytorch quantization memory-efficient adam-optimizer fine-tuning low-rank optimizers low-bit llm-training 8bit-optimizer adafactor memory-efficient-training optimizer-research apollo-optimizer came-optimizer optimizer-quantization

Updated Sep 9, 2026
Python

AubakirovArman / WAL-Ternary-8B

Star

2.898-BPW Qwen3-8B with direct-packed CPU/CUDA inference

cuda quantization ternary low-bit llm-inference qwen3

Updated Aug 7, 2026
Python

CrazyAngelm / megaquant-kv-cache

Star

Efficient low-bit KV-cache compression research with honest metadata accounting.

compression research inference quantization low-bit kv-cache llm

Updated Apr 24, 2026
Python

omgbox / TriLite.jl

Star

Pure-Julia CPU inference engine for BitNet b1.58 ternary LLMs

open-source machine-learning cpu ai deep-learning julia inference simd transformer high-performance-computing quantization ternary julialang bitnet low-bit ternary-weights llm

Updated Jun 17, 2026
Julia

shrut2702 / microscaling-formats

Star

Microscaling (MX) low-bit quantization formats, implemented and benchmarked on VLMs.

inference quantization vlm low-bit microscaling

Updated Aug 16, 2026
Jupyter Notebook

Quixyl-eng / exvram-lab

Star

Compute-for-memory research lab for running larger LLMs on memory-constrained consumer GPUs.

benchmarking machine-learning gpu cuda inference quantization rtx vram low-bit blackwell llm local-llm

Updated Sep 23, 2026

theomgdev / letfit

Star

Quantization toolkit for large language models: run and store huge models on small VRAM. Inspired by Unsloth's dynamic quantization.

python ai pytorch quantization model-compression vram low-bit llm llm-inference gguf

Updated Sep 11, 2026

BusySloths / slothbit

Sponsor

Star

A local testbed for 1-bit and ternary neural networks, BitNet research, and low-bit LLM inference.

python uv 1-bit bitnet low-bit llama-cpp local-llm ternary-neural-networks

Updated Sep 23, 2026
Python

shrut2702 / vlm-microscaling-benchmark

Star

inference quantization vlm low-bit microscaling

Updated Aug 16, 2026
Jupyter Notebook

Add this topic to your repo

To associate your repository with the low-bit topic, visit your repo's landing page and select "manage topics."

Learn more