nowfound

Alternatives

Products that do what Lossless compressor that can shrink llama3 to 68% does

  1. 18F

    Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…

    2023 · github.com

  2. 2AI
  3. 3

    New LLM compression algorithm by Google

    Mar 2026 · research.google

  4. 4
    Unsloth241

    Finetune LLMs 2x faster, 80% less memory

    2025

  5. 5TA
  6. 6JI

    2017 · github.com

  7. 7L3
  8. 8IM

    2025 · image-compressor-five-azure.vercel.app

  9. 9OS

    Stateful load balancer customized for llama.cpp (with a reverse proxy).

    2024 · github.com

  10. 10XC
  11. 11UF
  12. 12IM

    Jan 2026 · github.com

  13. 13OA

    I built an experiment that uses an overfitted transformer and arithmetic coding to compress individual files. Instead of training the model to generalize, I train a 900KB transformer to memorize a single file and predict the next byte. Those predictions are fed into an arithmetic coder to produce the compressed output. On a 100MB NYC taxi CSV, it compresses to about 7MB (~0.5 bits/byte). On a 100MB slice of enwik9, it compresses to about 21MB (~1.68 bits/byte). It's pretty slow right now (roughly 20–30 minutes of training and 45 minutes each for compression and decompression on my…

    Jun 2026

  14. 14ED
  15. 15TB
  16. 16DR
  17. 17CV

    2016 · compressify.herokuapp.com

  18. 18LL
  19. 19AB

    2019 · github.com

  20. 20TE
  21. 21CS

    Feb 2026 · github.com

  22. 22CL
  23. 23LS
  24. 24AL

    2011 · wearekiss.com

Ranked by how close each launch is in meaning, then by votes. Refine with a description →