T5

T5 V1_1 Xl

GGUFGGUF by jukkim046Updated 2025-02-17
Download on Hugging Face
Parameters2.85B
Context512
Layers24
Architecturet5
Smallest quant2.3 GB
Quick answer

T5 V1_1 Xl needs about 4.5 GB of memory at Q6_K (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU.

T5 V1_1 Xl is a 2.85B-parameter model in GGUF format, quantized by jukkim046. Its trained context length is 512 tokens. The repository has 1 quant file, from 2.3 GB (Q6_K) to 2.3 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K2.3 GB 2.9 GB
Fits Get file →

What GPU do you need for T5 V1_1 Xl?

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: the best quant that fits is Q6_K (2.3 GB file, about 4.5 GB in use).

Which T5 V1_1 Xl quant should you choose?

Q6_K (2.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturet5
Parameters2.85B
Layers24
Trained context512 tokens
KV cache (fp16)192 KB per token

Source

Quantized byjukkim046
Licenseapache-2.0
Downloads (HF)8
Last updated2025-02-17

Frequently asked questions about T5 V1_1 Xl

How much VRAM does T5 V1_1 Xl need?

About 4.5 GB at Q6_K with an 8K context window. That is the 2.3 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 T5 V1_1 Xl on an 8 GB GPU?

Yes, with Q6_K: the 2.3 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of T5 V1_1 Xl GGUF?

It depends on the quant: Q6_K is 2.3 GB.

What context length does T5 V1_1 Xl support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.1 GB at 512.

Where can I download T5 V1_1 Xl GGUF?

The files are on Hugging Face in the jukkim046/t5-v1_1-xl-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does T5 V1_1 Xl 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.

Other GGUFs of t5-v1_1-xl

Similar models

Browse all →

More from jukkim046

All by jukkim046 →

Other tiny models

All tiny models →