LA

gguf sharded LaMini Flan T5 248M

LaminiGGUF by FelladrinUpdated 2024-08-05
Download on Hugging Face
Parameters248M
Context512
Layers12
Architecturet5
Smallest quant0.3 GB
Quick answer

gguf sharded LaMini Flan T5 248M needs about 1.2 GB of memory at Q5_K_S (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

gguf sharded LaMini Flan T5 248M is a 248M-parameter Lamini model in GGUF format, quantized by Felladrin. Its trained context length is 512 tokens. The repository has 1 quant file, from 0.3 GB (Q5_K_S) to 0.3 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S0.3 GB (7 parts) 0.9 GB
Fits Get file →

What GPU do you need for gguf sharded LaMini Flan T5 248M?

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: the best quant that fits is Q5_K_S (0.3 GB file, about 1.2 GB in use).

Which gguf sharded LaMini Flan T5 248M quant should you choose?

Q5_K_S (0.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturet5
Parameters248M
Layers12
Trained context512 tokens
KV cache (fp16)36 KB per token

Source

Quantized byFelladrin
FamilyLamini
Downloads (HF)119
Last updated2024-08-05

Frequently asked questions about gguf sharded LaMini Flan T5 248M

How much VRAM does gguf sharded LaMini Flan T5 248M need?

About 1.2 GB at Q5_K_S with an 8K context window. That is the 0.3 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 gguf sharded LaMini Flan T5 248M on an 8 GB GPU?

Yes, with Q5_K_S: the 0.3 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gguf sharded LaMini Flan T5 248M GGUF?

It depends on the quant: Q5_K_S is 0.3 GB.

What context length does gguf sharded LaMini Flan T5 248M support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 512.

Where can I download gguf sharded LaMini Flan T5 248M GGUF?

The files are on Hugging Face in the Felladrin/gguf-sharded-LaMini-Flan-T5-248M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gguf sharded LaMini Flan T5 248M use?

Hugging Face lists the license as cc-by-nc-4.0. 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 LaMini-Flan-T5-248M

Similar models

Browse all →

More from Felladrin

All by Felladrin →

More Lamini models

All Lamini →

Other tiny models

All tiny models →