TI

Tifa Deepsex 14b CoT

TifaGGUF by ValueFX9507Updated 2025-02-13
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant29.5 GB
Quick answer

Tifa Deepsex 14b CoT needs about 31.7 GB of memory at F16 (a 29.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 29.5 GB (F16) to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Tifa Deepsex 14b CoT is a 14.8B-parameter Tifa model in GGUF format, quantized by ValueFX9507. Its trained context length is 128K tokens. The repository has 3 quant files, from 29.5 GB (F16) to 29.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1629.5 GB 31.7 GB
Too big Get file →
F1629.5 GB 31.7 GB
Too big Get file →
F1629.5 GB 31.7 GB
Too big Get file →

What GPU do you need for Tifa Deepsex 14b CoT?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is F16 (29.5 GB file, about 31.7 GB in use).

Which Tifa Deepsex 14b CoT quant should you choose?

F16 (29.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is F16 at 29.5 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized byValueFX9507
FamilyTifa
Licenseapache-2.0
Downloads (HF)373
Last updated2025-02-13

Frequently asked questions about Tifa Deepsex 14b CoT

How much VRAM does Tifa Deepsex 14b CoT need?

About 31.7 GB at F16 with an 8K context window. That is the 29.5 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 Tifa Deepsex 14b CoT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Tifa Deepsex 14b CoT GGUF?

It depends on the quant: F16 is 29.5 GB, F16 is 29.5 GB, F16 is 29.5 GB.

What context length does Tifa Deepsex 14b CoT support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Tifa Deepsex 14b CoT GGUF?

The files are on Hugging Face in the ValueFX9507/Tifa-Deepsex-14b-CoT repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Tifa Deepsex 14b CoT use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from ValueFX9507

All by ValueFX9507 →

More Tifa models

All Tifa →

Other medium models

All medium models →