TA

Taste Test 3B

TasteGGUF by jeikuUpdated 2023-12-26
Download on Hugging Face
Parameters2.8B
Context4K
Layers32
Architecturestablelm
Smallest quant5.6 GB
Quick answer

Taste Test 3B needs about 8.8 GB of memory at F16 (a 5.6 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Taste Test 3B is a 2.8B-parameter Taste model in GGUF format, quantized by jeiku. Its trained context length is 4K tokens. The repository has 1 quant file, from 5.6 GB (F16) to 5.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F165.6 GB 7.4 GB
Tight Get file →

What GPU do you need for Taste Test 3B?

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: the best quant that fits is F16 (5.6 GB file, about 8.8 GB in use).

Which Taste Test 3B quant should you choose?

F16 (5.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestablelm
Parameters2.8B
Layers32
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byjeiku
FamilyTaste
Licenseother
Downloads (HF)47
Last updated2023-12-26

Frequently asked questions about Taste Test 3B

How much VRAM does Taste Test 3B need?

About 8.8 GB at F16 with an 8K context window. That is the 5.6 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 Taste Test 3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Taste Test 3B GGUF?

It depends on the quant: F16 is 5.6 GB.

What context length does Taste Test 3B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Taste Test 3B GGUF?

The files are on Hugging Face in the jeiku/Taste_Test_3B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Taste Test 3B use?

Hugging Face lists the license as other. 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 jeiku

All by jeiku →

More Taste models

All Taste →

Other tiny models

All tiny models →