3T

3T

GGUFGGUF by Ak1104Updated 2024-08-10
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

3T needs about 6.5 GB of memory at Q4_0 (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU.

3T is a 8.03B-parameter model in GGUF format, quantized by Ak1104. Its trained context length is 8K tokens. The repository has 1 quant file, from 4.9 GB (Q4_0) to 4.9 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.9 GB 6.5 GB
Fits Get file →

What GPU do you need for 3T?

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: the best quant that fits is Q4_0 (4.9 GB file, about 6.5 GB in use).

Which 3T quant should you choose?

Q4_0 (4.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byAk1104
RepositoryAk1104/3T
Licensellama3
Downloads (HF)18
Last updated2024-08-10

Frequently asked questions about 3T

How much VRAM does 3T need?

About 6.5 GB at Q4_0 with an 8K context window. That is the 4.9 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 3T on an 8 GB GPU?

Yes, with Q4_0: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of 3T GGUF?

It depends on the quant: Q4_0 is 4.9 GB.

What context length does 3T support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download 3T GGUF?

The files are on Hugging Face in the Ak1104/3T repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does 3T use?

Hugging Face lists the license as llama3. 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 Ak1104

All by Ak1104 →

Other small models

All small models →