KvcHub Labs

Small language models, built from scratch.

KaiLu is the KvcHub Labs family of chat models. Every checkpoint is trained from random initialization and sized to run offline on your own machine. KaiLu 3 is the newest and the best of them: pretrained on 6.6B tokens, then tuned with supervised fine-tuning and DPO, in just 329M parameters.

ollama run hf.co/KvcHub/KaiLu3
Compare the models
Parameters KaiLu family
  1. KaiLu 3best, newest329M
  2. KaiLu 2 933M933M
  3. KaiLu 2 2B1.90B

The KaiLu family

Every KaiLu model is trained from random initialization. They borrow LFM2's hybrid layout of short-convolution and attention layers, not its weights.

  • Text GenerationBestNewest0.3B

    KaiLu 3

    KvcHub/KaiLu3

    Our newest and best model. Pretrained on 6.6B tokens of web, textbook, math and code data, then tuned with supervised fine-tuning and DPO. Start here.

    Parameters
    329M
    Layers
    24 (16 conv, 8 attn)
    Context
    1,024 tokens
    License
    Free for personal use
    Run it Model card
  • Text Generation2B · GGUF

    KaiLu 2 2B

    KvcHub/KaiLu-2-2B-GGUF

    The largest KaiLu, trained on a single Mac. It works through math, code and logic step by step before it answers.

    Parameters
    1.90B
    Layers
    104 (68 conv, 36 attn)
    Context
    1,024 trained, 4,096 max
    License
    Apache 2.0
    Run it Model card
  • Text Generation1.0B

    KaiLu 2 933M

    KvcHub/KaiLu-2-933M

    Built with MLX for Apple silicon, with a 546 MB GGUF build sized for phones.

    Parameters
    933M
    Speed
    260+ tok/s on Apple silicon
    Mobile RAM
    1.15 GB
    License
    Apache 2.0
    Run it Model card

All KaiLu models work best in English and can state wrong facts confidently, so they aren't meant for high-stakes use. KaiLu 3 is free for personal use, study and modification; for business use, email hello@kvchub.com first.

Run KaiLu on your machine

Pick a model and a runtime. Commands come straight from each model card.

Model
Runtime
Terminal 
$ ollama run hf.co/KvcHub/KaiLu3

Best in English and within 1,024 tokens of context.

A quick look at Kava

Kava is the lab's pair of tiny token classifiers, at 636k and 2.01M parameters. They replace personal details with placeholders like [EMAIL] and [PHONE] before text is logged or sent to a language model. Try a browser version below; your text never leaves this page.

0 chars
Redacted output
Redacted text appears here.
Latency
–
Tokens
–
Memory (est.)
–
Sent over network
0 B
  • [EMAIL]0
  • [PHONE]0
  • [CARD]0
  • [IP]0

The browser demo uses lightweight pattern rules so it runs anywhere, with latency measured live on your device. The real Kava models do learned token classification in Python. Memory estimates assume fp16 weights plus the text buffers.

Install

pip install kava-privacy
PyPI Kava-Privacy-636k-mlx Kava-Privacy-2.01M-mlx

Speed per request

KvcHub on-device inference<1 ms
Cloud DLP / LLM API round trip~130 ms+
Hatched time is spent on the network and in someone else's queue. Cloud figure is typical and varies by provider and region.