Skip to content

Benchmarking Project · Python

turboquant-local

TurboQuant KV-cache optimization for AMD Radeon 890M (gfx1150) with Vulkan backend - work in progress

What it is

This repository provides a benchmarking harness and documentation for evaluating TurboQuant KV-cache optimization in llama.cpp, including quantization implementation and setup scripts, but relies on an external fork for the actual TurboQuant integration.

Scored at264df6618 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
NLP & LLMs: 40.0%Machine Learning: 35.0%MLOps: 15.0%Data Science: 10.0%
  • NLP & LLMs40%
  • Machine Learning35%
  • MLOps15%
  • Data Science10%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths3

  • Comprehensive documentation and analysis of TurboQuant integration options
  • Implemented quantization code (Lloyd-Max, rotation) and benchmarking harness
  • Actual benchmark runs have been performed and results stored

Limitations

The owner keeps this project's limitations private.

Around it on the NLP & LLMs board

Whole board
  1. 113Ai-In-Education-Sentiment-AnalysisTutorial / Demo · Jupyter Notebook51.9/100ImplementationDaffa
  2. 114lemonadecliML Application · Rust51.7/100ImplementationMurat Genç
  3. 115turboquant-localBenchmarking Project · Python51.2/100ImplementationFulvio
  4. 116, shared rankai-service-chatbotRAG System · Python50.7/100ImplementationJens Mittelbach
  5. 116, shared ranklangflow-796xAI Developer Tool · TypeScript50.7/100ImplementationPetr Sovadina

More from Fulvio