TaQuants/Tema_Q-X4-Thinking-TaQuants-GGUF

Tema_Q-X4-Thinking TaQuants

The Repository Technical Report

The TemaQ 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/TemaQ-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 | | --- | --- | --- | | IQ2M | 10.40 | 41.10 | | TaIQ2M | 11.10 | 45.62 | | IQ3S | 12.20 | 50.14 | | TaIQ3S | 12.60 | 50.23 |