QU

quantized

QuantizedGGUF by stephen-stecklerUpdated 2023-11-28
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

quantized needs about 6.3 GB of memory at F16 (a 1.5 GB file) with an 8K context window, so it fits on a 8 GB GPU.

quantized is a 6.74B-parameter Quantized model in GGUF format, quantized by stephen-steckler. Its trained context length is 4K tokens. The repository has 1 quant file, from 1.5 GB (F16) to 1.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.5 GB 4.1 GB
Fits Get file →

What GPU do you need for quantized?

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 F16 (1.5 GB file, about 6.3 GB in use).

Which quantized quant should you choose?

F16 (1.5 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bystephen-steckler
FamilyQuantized
Downloads (HF)23
Last updated2023-11-28

Frequently asked questions about quantized

How much VRAM does quantized need?

About 6.3 GB at F16 with an 8K context window. That is the 1.5 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 quantized on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of quantized GGUF?

It depends on the quant: F16 is 1.5 GB.

What context length does quantized support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download quantized GGUF?

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

Similar models

Browse all →

More Quantized models

All Quantized →

Other small models

All small models →