---
base_model:
- temaq-org/Tema_Q-X6-Thinking
pipeline_tag: text-generation
tags:
- TaQuants
- uncensored
- non-censored
- unfiltered
---
# Tema_Q-X6-Thinking TaQuants

![image/jpg](https://huggingface.co/TaQuants/Tema_Q-X6-Thinking-TaQuants-GGUF/resolve/main/agent.png)

[The Repository](https://github.com/ek15072809/TaQuants)  
[Technical Report](https://github.com/ek15072809/TaQuants/blob/main/docs/TaQuants_Technical_Report.pdf)

The Tema_Q development team, team zenei, has developed a new importance matrix method called **TaQuants (Tensor-aware Adaptive Quantization)**.  
This model is a TaQuants version of [temaq-org/Tema_Q-X6-Thinking](https://huggingface.co/temaq-org/Tema_Q-X6-Thinking) created with TaQuants v3.0. 

When combined with the [Tema_Q Agent](https://github.com/ek15072809/Tema_Q-Agent), it performs agent functions. This TaQuants model maintains performance equivalent to 4 bits without collapsing.