GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

TaQuants/Tema_Q-X7-Thinking-TaQuants-GGUF overview

Tema Q X7 Thinking TaQuants The Repository https://github.com/ek15072809/TaQuants Technical Report https://github.com/ek15072809/TaQuants/blob/main/docs/TaQuan…

ggufTaQuantsuncensorednon-censoredunfilteredtext-generationbase_model:temaq-org/Tema_Q-X7-Thinkingbase_model:quantized:temaq-org/Tema_Q-X7-Thinkingendpoints_compatibleregion:usimatrixconversational

Runs locally from ~441.8 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
12
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

7 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
IQ2_M/Tema_Q-X7-Thinking-TaIQ2_M-split.gguf-00001-of-00007.ggufGGUFIQ2_M1.83 GBDownload
IQ2_M/Tema_Q-X7-Thinking-TaIQ2_M-split.gguf-00002-of-00007.ggufGGUFIQ2_M1.84 GBDownload
IQ2_M/Tema_Q-X7-Thinking-TaIQ2_M-split.gguf-00003-of-00007.ggufGGUFIQ2_M1.81 GBDownload
IQ2_M/Tema_Q-X7-Thinking-TaIQ2_M-split.gguf-00004-of-00007.ggufGGUFIQ2_M1.81 GBDownload
IQ2_M/Tema_Q-X7-Thinking-TaIQ2_M-split.gguf-00005-of-00007.ggufGGUFIQ2_M1.82 GBDownload
IQ2_M/Tema_Q-X7-Thinking-TaIQ2_M-split.gguf-00006-of-00007.ggufGGUFIQ2_M1.85 GBDownload
IQ2_M/Tema_Q-X7-Thinking-TaIQ2_M-split.gguf-00007-of-00007.ggufGGUFIQ2_M441.8 MBDownload

Model Details

Model IDTaQuants/Tema_Q-X7-Thinking-TaQuants-GGUF
AuthorTaQuants
Pipelinetext-generation
License
Base modeltemaq-org/Tema_Q-X7-Thinking
Last modified2026-08-23T12:20:51.000Z

Model README

---

base_model:

  • temaq-org/Tema_Q-X7-Thinking

pipeline_tag: text-generation

tags:

  • TaQuants
  • uncensored
  • non-censored
  • unfiltered

---

Tema_Q-X7-Thinking TaQuants

The Repository

Technical Report

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-X7-Thinking created with TaQuants v3.0.

When combined with the Tema_Q Agent, it performs agent functions.

We used This imatrix gguf for I1-Quants. Thanks.

While this does not significantly impact the execution of agent tools, there is a risk of model breakdown when generating more than 8k tokens. This is highly likely to be a characteristic specific to the model itself.

Run TaQuants/Tema_Q-X7-Thinking-TaQuants-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models