Embedding Compression Benchmark

All compression techniques evaluated with 4-bit quantization.

Method Overview

Method	When it Trains	Training Hardware / Time	Data Needed
MRL	During model training	Full training pipeline	Base training data
SVD	Post-hoc	CPU	~40k samples
Proposed	Post-hoc	GPU (<20s on A100)	~40k samples

Ours is consistently SOTA and surpassing previous baselines by a significant measure.

Dataset	Metric	MRL	SVD	Proposed	Gain vs. SVD
MXBAI FIQA	Recall@200	0.41	0.59	0.63	+6.8%
NOMIC FIQA	Recall@200	0.42	0.47	0.55	+17.0%
NOMIC TREC-COVID	Recall@200	0.12	0.11	0.14	+27.3%

Although the benefit is less then at 32 dim, ours is still significantly better then MRL and SVD.

Dataset	Metric	MRL	SVD	Proposed	Gain vs. SVD
MXBAI FIQA	Recall@200	0.57	0.71	0.71	0.0%
NOMIC FIQA	Recall@200	0.60	0.62	0.65	+4.8%
NOMIC TREC-COVID	Recall@200	0.17	0.15	0.17	+13.3%

Pipeline: 32-dim IVF index to get top 200 and then 256 dim retrieves top 10.

Once again, ours is SOTA while retaining over 94% of the overall quality.

Dataset	Original (Full)	MRL	SVD	Proposed	% Retention of Original
MXBAI FIQA	0.45	0.34	0.40	0.43	95.6%
NOMIC FIQA	0.37	0.30	0.31	0.35	94.1%
NOMIC TREC-COVID	0.70	0.70	0.69	0.70	100.0%

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution for coala-embeddings 0.1.2
File	Size	Uploaded
coala_embeddings-0.1.2.tar.gz	12.5 kB	Aug 13, 2026	Details

Table of built distributions (wheels) for coala-embeddings 0.1.2
File	Interpreter	ABI	Platform	Reset
coala_embeddings-0.1.2-py3-none-any.whl 13.4 kB Aug 13, 2026	Python 3	none	any	Details

Total release size: 25.9 kB

Download URL	coala_embeddings-0.1.2.tar.gz
Size	12.5 kB
Tags	Source
SHA-256 checksum How to use checksums	`4993d4e9411c3cd30ea6c4d445109aeb1d1a3d7b10799ee8fab6ad9f57367ca7`
BLAKE2b-256 checksum How to use checksums	`f433b8057f403d2492ee58881ae27a927fbf531bb0dd28d50d7d8cd7f166a9cb`
Upload date	Aug 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.13`

Download URL	coala_embeddings-0.1.2-py3-none-any.whl
Size	13.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`620fe7f6a3e7e0c3f224fe144eb220e12dc4cfb256fd1620c1114824c98e316d`
BLAKE2b-256 checksum How to use checksums	`60e6b17bbe54642f081cff7e76cc44c15aaa4ea59e64a1581b96466f6b0e0f43`
Upload date	Aug 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.13`