MA

mamba-ko-2.8b

MambaGGUF by yoonjae22Updated 2024-03-12
Download on Hugging Face
Parameters2.77B
Context1024K
Layers64
Architecturemamba
Smallest quant5.8 GB
Quick answer

mamba-ko-2.8b needs about 7.0 GB of memory at F16 (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU.

mamba-ko-2.8b is a 2.77B-parameter Mamba model in GGUF format, quantized by yoonjae22. Its trained context length is 1024K tokens. The repository has 1 quant file, from 5.8 GB (F16) to 5.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F165.8 GB 7.0 GB
Fits Get file →

What GPU do you need for mamba-ko-2.8b?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (5.8 GB file, about 7.0 GB in use).

Which mamba-ko-2.8b quant should you choose?

F16 (5.8 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

Architecturemamba
Parameters2.77B
Layers64
Trained context1,048,576 tokens

Source

Quantized byyoonjae22
FamilyMamba
Downloads (HF)9
Last updated2024-03-12

Frequently asked questions about mamba-ko-2.8b

How much VRAM does mamba-ko-2.8b need?

About 7.0 GB at F16 with an 8K context window. That is the 5.8 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 mamba-ko-2.8b on an 8 GB GPU?

Yes, with F16: the 5.8 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mamba-ko-2.8b GGUF?

It depends on the quant: F16 is 5.8 GB.

What context length does mamba-ko-2.8b support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download mamba-ko-2.8b GGUF?

The files are on Hugging Face in the yoonjae22/mamba-ko-2.8b-GGUF 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 yoonjae22

All by yoonjae22 →

More Mamba models

All Mamba →

Other tiny models

All tiny models →