Research / 02
Work that can
be inspected.
Research is useful when someone else can challenge it, rerun it and build on it. We publish the method, the artifacts and the uncomfortable details.
Open arXiv:2603.04162BS / RESEARCH02
Bielik Q2 Sharp
How small can a model get
without losing its language?
The published study, led by BitSharp founder Jakub Prejzner, compares six 2 bit quantization methods across 22 Polish benchmark suites. It measures the tradeoff instead of hiding it.
FP16 baseline22GB
→Quantized model3.26GB
Public infrastructure
The result is not
a screenshot.
The paper is only the index. Models, datasets, Hessians and evaluation traces make the work inspectable.
01
Models9 public releases
02Datasets3 public datasets
03PublicationarXiv:2603.04162
04
Agent evaluationPolAgentBench, 67 task draft
In developmentMethod
01
Make the claim precise.
No broad quality label. Name the metric, baseline and evaluation set.
02
Expose the route to it.
Keep the code, weights and evaluation artifacts close to the conclusion.
03
State what did not work.
A real result includes caveats, failure modes and methodological limits.
Build from evidence