TaQuants/Tema_Q-R-4B-TaQuants-GGUF overview
Tema Q R 4B TaQuants The Repository https://github.com/ek15072809/TaQuants Technical Report https://github.com/ek15072809/TaQuants/blob/main/docs/TaQuants Tech…
Runs locally from ~1.43 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | TaQuants/Tema_Q-R-4B-TaQuants-GGUF |
|---|---|
| Author | TaQuants |
| Pipeline | text-generation |
| License | — |
| Base model | temaq-org/Tema_Q-R-4B |
| Last modified | 2026-07-03T10:46:44.000Z |
Model README
---
base_model:
- temaq-org/Tema_Q-R-4B
pipeline_tag: text-generation
tags:
- TaQuants
- uncensored
- non-censored
- unfiltered
---
Tema_Q-R-4B TaQuants
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.
Run TaQuants/Tema_Q-R-4B-TaQuants-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models