BA

BangLaMA

BanglamaGGUF by abushuvomUpdated 2024-04-16
Download on Hugging Face
Parameters13.2B
Context4K
Layers40
Architecturellama
Smallest quant8.0 GB
Quick answer

BangLaMA needs about 15.2 GB of memory at F32 (a 8.0 GB file) with an 8K context window, so it fits on a 16 GB GPU.

BangLaMA is a 13.2B-parameter Banglama model in GGUF format, quantized by abushuvom. Its trained context length is 4K tokens. The repository has 1 quant file, from 8.0 GB (F32) to 8.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F328.0 GB 11.9 GB
Too big Get file →

What GPU do you need for BangLaMA?

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: the best quant that fits is F32 (8.0 GB file, about 15.2 GB in use).

Which BangLaMA quant should you choose?

F32 (8.0 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
Parameters13.2B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byabushuvom
FamilyBanglama
Licensemit
Downloads (HF)10
Last updated2024-04-16

Frequently asked questions about BangLaMA

How much VRAM does BangLaMA need?

About 15.2 GB at F32 with an 8K context window. That is the 8.0 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 BangLaMA on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BangLaMA GGUF?

It depends on the quant: F32 is 8.0 GB.

What context length does BangLaMA support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download BangLaMA GGUF?

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

What license does BangLaMA 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.

Similar models

Browse all →

Other medium models

All medium models →