cmix is a lossless data compression program aimed at optimizing compression ratio at the cost of high CPU/memory usage. It gets state of the art results on several compression benchmarks. cmix is free software distributed under the GNU General Public License.

cmix works in Linux, Windows, and Mac OS X. At least 32GB of RAM is recommended to run cmix. Feel free to contact me at if you have any questions.

GitHub repository:


Source Code Release Date Windows Executable May 5, 2018 October 20, 2017 April 24, 2017 November 7, 2016 July 3, 2016 May 30, 2016 April 8, 2016 November 10, 2015 February 4, 2015 September 2, 2014 August 13, 2014 July 23, 2014 June 27, 2014 May 29, 2014 April 13, 2014


Corpus Original size
Compressed size
Compression time
Memory usage
calgary.tar 3152896 545501 2537.39 22827744
silesia 211938580 29241785
enwik6 1000000 179426 744.68 20593812
enwik8 100000000 15111677 64051.17 24077960
enwik9 1000000000 117959016 650055.7 28365564

Compression and decompression time are symmetric. The compressed size can vary slightly depending on the compiler settings used to build the executable.

External Benchmarks

Silesia Open Source Compression Benchmark

File Original size
Compressed size
dickens 10192446 1840392
mozilla 51220480 7161756
mr 9970564 1912673
nci 33553445 811610
ooffice 6152192 1256130
osdb 10085684 1969208
reymont 6627202 736373
samba 21606400 1642789
sao 7251944 3732491
webster 41458703 4413876
xml 5345280 239434
x-ray 8474240 3525053

Calgary Corpus

File Original size
Compressed size
BIB 111261 17581
BOOK1 768771 176459
BOOK2 610856 108340
GEO 102400 43104
NEWS 377109 78484
OBJ1 21504 7131
OBJ2 246814 40712
PAPER1 53161 11016
PAPER2 82199 17432
PIC 513216 22140
PROGC 39611 8479
PROGL 71646 9059
PROGP 49379 6361
TRANS 93695 10232

Canterbury Corpus

File Original size
Compressed size
alice29.txt 152089 31484
asyoulik.txt 125179 29766
cp.html 24603 4861
fields.c 11150 1990
grammar.lsp 3721 795
kennedy.xls 1029744 8290
lcet10.txt 426754 74679
plrabn12.txt 481861 113460
ptt5 513216 22140
sum 38240 7009
xargs.1 4227 1153


I started working on cmix in December 2013. Most of the ideas I implemented came from the book Data Compression Explained by Matt Mahoney.

cmix uses three main components:

  1. Preprocessing
  2. Model prediction
  3. Context mixing

The preprocessing stage transforms the input data into a form which is more easily compressible. This data is then compressed using a single pass, one bit at a time. cmix generates a probabilistic prediction for each bit and the probability is encoded using arithmetic coding.

cmix uses an ensemble of independent models to predict the probability of each bit in the input stream. The model predictions are combined into a single probability using a context mixing algorithm. The output of the context mixer is refined using an algorithm called secondary symbol estimation (SSE).




cmix uses a transformation on three types of data:

  1. Binary executables
  2. Natural language text
  3. Images

The preprocessor uses separate components for detecting the type of data and actually doing the transformation.

For images and binary executables, I used code for detection and transformation from the open source paq8pxd program.

I wrote my own code for detecting natural language text. For transforming the text, I used code from the open source paq8hp12any program. This uses an English dictionary and a word replacing transform. The dictionary is 463,903 bytes.

As seen on the Silesia benchmark, additional preprocessing using the precomp program can improve cmix compression on some files.

Model Prediction

cmix v15 uses a total of 2,203 independent models. There are a variety of different types of models, some specialized for certain types of data such as text, executables, or images. For each bit of input data, each model outputs a single floating point number, representing the probability that the next bit of data will be a 1. The majority of the models come from other open source compression programs: paq8l, paq8pxd, and paq8hp12any.

LSTM Mixer


The byte-level mixer uses long short-term memory (LSTM) trained using backpropagation through time. I created another project called lstm-compress which compresses data using only LSTM.

Context Mixing


cmix uses a similar neural network architecture to paq8. This architecture is also known as a gated linear network. cmix uses three layers of weights.


Thanks to AI Grant for funding cmix.

cmix uses ideas and source code from many people in the data compression community. Here are some of the major contributors: