LO

LocAlM

LocalmGGUF by potion-verteUpdated 2024-05-02
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant2.3 GB
Quick answer

LocAlM needs about 6.4 GB of memory at its main file (a 2.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 2.3 GB to 7.6 GB.

LocAlM is a 3.82B-parameter Localm model in GGUF format, quantized by potion-verte. Its trained context length is 4K tokens. The repository has 3 quant files, from 2.3 GB to 7.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.3 GB 4.4 GB
Fits Get file →
—2.6 GB 4.8 GB
Fits Get file →
—7.6 GB 9.8 GB
Too big Get file →

What GPU do you need for LocAlM?

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: the best quant that fits is the main file (2.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (2.6 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.6 GB file, about 11.4 GB in use).

Which LocAlM quant should you choose?

If memory is tight, the smallest file is the first one in the table at 2.3 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized bypotion-verte
FamilyLocalm
Downloads (HF)5
Last updated2024-05-02

Frequently asked questions about LocAlM

How much VRAM does LocAlM need?

About 6.4 GB at its main file with an 8K context window. That is the 2.6 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 LocAlM on an 8 GB GPU?

Yes, with the smaller files: the 2.6 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LocAlM GGUF?

It depends on the quant: file is 2.3 GB, file is 2.6 GB, file is 7.6 GB.

What context length does LocAlM support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download LocAlM GGUF?

The files are on Hugging Face in the potion-verte/LocAlM 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 →

Other small models

All small models →