CO

Contif16

ContifGGUF by mezzihoussemUpdated 2024-08-14
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant13.5 GB
Quick answer

Contif16 needs about 18.3 GB of memory at its main file (a 13.5 GB file) with an 8K context window, so it fits on a 24 GB GPU.

Contif16 is a 6.74B-parameter Contif model in GGUF format, quantized by mezzihoussem. Its trained context length is 16K tokens. The repository has 1 quant file, from 13.5 GB to 13.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—13.5 GB 18.3 GB
Too big Get file →

What GPU do you need for Contif16?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is the main file (13.5 GB file, about 18.3 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymezzihoussem
FamilyContif
Downloads (HF)12
Last updated2024-08-14

Frequently asked questions about Contif16

How much VRAM does Contif16 need?

About 18.3 GB at its main file with an 8K context window. That is the 13.5 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 Contif16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Contif16 GGUF?

It depends on the quant: file is 13.5 GB.

What context length does Contif16 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download Contif16 GGUF?

The files are on Hugging Face in the mezzihoussem/Contif16 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 from mezzihoussem

All by mezzihoussem →

Other small models

All small models →