Tema Q X4 Thinking TaQuants GGUF | Sweet Tea Studio
ModelVerifiedExternal
Tema Q X4 Thinking TaQuants GGUF
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-X4-Thinking created with TaQuants v2.8.
--- base_model: - temaq-org/Tema_Q-X4-Thinking pipeline_tag: text-generation tags: - TaQuants - uncensored - non-censored - unfiltered --- # Tema_Q-X4-Thinking TaQuants [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-X4-Thinking](https://huggingface.co/temaq-org/Tema_Q-X4-Thinking) created with TaQuants v2.8. The model size and performance are as follows: | | Size (GB) | Knowledge score | | --- | --- | --- | | IQ2_M | 10.40 | 41.10 | | TaIQ2_M | 11.10 | 45.62 | | IQ3_S | 12.20 | 50.14 | | TaIQ3_S | 12.60 | 50.23 |
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-X4-Thinking created with TaQuants v2.8.
