ModelÜberprüftExtern

Tema Q R 4B TaQuants GGUF

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-R-4B created with...

Quellehuggingface.co/TaQuants/Tema_Q-R-4B-TaQuants-GGUF/tree/9f2b15c228d88d6942e7f248b59c10017cc10bcb

ArtOtherBasismodelltemaq-org/Tema_Q-R-4BVersionRevision 9f2b15cVerleger@temaq-orgCBewertung

Modellquelle

Art: Other
Dateigröße: 1,43–1,96 GB
Basismodell: temaq-org/Tema_Q-R-4B
Version: vRevision 9f2b15c
Aktualisiert: 3. Okt. 2026
Verleger: @temaq-org
Downloads: 49
Parameter: 4B
Aufgaben: Textgenerierung
Quelle: Hugging Face

Quellenbeschreibung

Tema_Q-R-4B 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-R-4B created with TaQuants v2.0.

The model size and performance are as follows:
TaIQ2_M is 0.01GB compressed and shows a 0.96% improvement in PPL compared to IQ2_M. TaIQ3_S has a file size increase of 0.16GB compared to IQ3_S. On the other hand, it shows a 3.43% improvement in PPL compared to Q4_K_M, which is 0.35GB larger.

Quellen

1 Quelle

Hugging FacePrimärVersion 9f2b15c228d88d6942e7f248b59c10017cc10bcb

huggingface.co/TaQuants/Tema_Q-R-4B-TaQuants-GGUF/tree/9f2b15c228d88d6942e7f248b59c10017cc10bcb

Verifiziert 3. Okt.

Modellartefakte

2 Artefakte

Tema_Q-R-4B-TaIQ2_M.gguf

gguf · 1,43 GB · SHA-256 34e46a180c7d…8ad4 · Hugging Face

Herunterladen

Tema_Q-R-4B-TaIQ3_S.gguf

gguf · 1,96 GB · SHA-256 10268f410ee7…da08 · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge

Readme11. Julihuggingface.co/TaQuants/Tema_Q-R-4B-TaQuants-GGUF

--- base_model: - temaq-org/Tema_Q-R-4B pipeline_tag: text-generation tags: - TaQuants - uncensored - non-censored - unfiltered --- # Tema_Q-R-4B 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-R-4B](https://huggingface.co/temaq-org/Tema_Q-R-4B) created with TaQuants v2.0. The model size and performance are as follows: TaIQ2_M is 0.01GB compressed and shows a 0.96% improvement in PPL compared to IQ2_M. TaIQ3_S has a file size increase of 0.16GB compared to IQ3_S. On the other hand, it shows a 3.43% improvement in PPL compared to Q4_K_M, which is 0.35GB larger.

Note3. Okt.huggingface.co/TaQuants/Tema_Q-R-4B-TaQuants-GGUF

Source context: 49 downloads · 0 likes · Pipeline text-generation · Repo TaQuants/Tema_Q-R-4B-TaQuants-GGUF

Note17. Julihuggingface.co/TaQuants/Tema_Q-R-4B-TaQuants-GGUF

Source context: 344 downloads · 0 likes · Pipeline text-generation · Repo TaQuants/Tema_Q-R-4B-TaQuants-GGUF