AdiTurbo TQ Models needs about 1.0 GB of memory at TQ4_0 (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.2 GB (TQ3_0) to 3.9 GB (TQ3_0).
AdiTurbo TQ Models is a 8.03B-parameter Aditurbo model in GGUF format, quantized by Adiuk. Its trained context length is 128K tokens. The repository has 4 quant files, from 0.2 GB (TQ3_0) to 3.9 GB (TQ3_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ3_0 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| TQ4_0 | 0.5 GB | 1.0 GB | Fits | Get file → | |
| TQ3_0 | 3.3 GB | 4.2 GB | Fits | Get file → | |
| TQ3_0 | 3.9 GB | 4.9 GB | Fits | Get file → |
What GPU do you need for AdiTurbo TQ Models?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is TQ4_0 (0.5 GB file, about 1.0 GB in use).
- 6 GB VRAM: the best quant that fits is TQ3_0 (3.9 GB file, about 4.9 GB in use).
Which AdiTurbo TQ Models quant should you choose?
TQ4_0 (0.5 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is TQ3_0 at 0.2 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AdiTurbo TQ Models
How much VRAM does AdiTurbo TQ Models need?
About 1.0 GB at TQ4_0 with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run AdiTurbo TQ Models on an 8 GB GPU?
Yes, with TQ3_0: the 3.9 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of AdiTurbo TQ Models GGUF?
It depends on the quant: TQ3_0 is 0.2 GB, TQ4_0 is 0.5 GB, TQ3_0 is 3.3 GB, TQ3_0 is 3.9 GB.
What context length does AdiTurbo TQ Models support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download AdiTurbo TQ Models GGUF?
The files are on Hugging Face in the Adiuk/AdiTurbo-TQ-Models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.