AL

Albacus V2 Imatrix

AlbacusGGUF by ClaudioItalyUpdated 2024-09-16
Download on Hugging Face
Parameters8.99B
Context32K
Layers40
Architecturellama
Smallest quant6.4 GB
Quick answer

Albacus V2 Imatrix needs about 8.2 GB of memory at Q5_K_M (a 6.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 6.4 GB (Q5_K_M) to 6.4 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Albacus V2 Imatrix is a 8.99B-parameter Albacus model in GGUF format, quantized by ClaudioItaly. Its trained context length is 32K tokens. The repository has 2 quant files, from 6.4 GB (Q5_K_M) to 6.4 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M6.4 GB 8.2 GB
Too big Get file →
Q5_K_M6.4 GB 8.2 GB
Too big Get file →

What GPU do you need for Albacus V2 Imatrix?

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 Q5_K_M (6.4 GB file, about 8.2 GB in use).

Which Albacus V2 Imatrix quant should you choose?

Q5_K_M (6.4 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

Architecturellama
Parameters8.99B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byClaudioItaly
FamilyAlbacus
Licensemit
Downloads (HF)93
Last updated2024-09-16

Frequently asked questions about Albacus V2 Imatrix

How much VRAM does Albacus V2 Imatrix need?

About 8.2 GB at Q5_K_M with an 8K context window. That is the 6.4 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 Albacus V2 Imatrix on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Albacus V2 Imatrix GGUF?

It depends on the quant: Q5_K_M is 6.4 GB, Q5_K_M is 6.4 GB.

What context length does Albacus V2 Imatrix support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Albacus V2 Imatrix GGUF?

The files are on Hugging Face in the ClaudioItaly/Albacus-V2-Imatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Albacus V2 Imatrix use?

Hugging Face lists the license as mit. 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 Albacus

Similar models

Browse all →

More from ClaudioItaly

All by ClaudioItaly →

More Albacus models

All Albacus →

Other small models

All small models →