MA

Mamba2 2.7b

MambaGGUF by TedlianghkUpdated 2025-08-05
Download on Hugging Face
Parameters2.83B
Context1024K
Layers64
Architecturemamba2
Smallest quant2.0 GB
Quick answer

Mamba2 2.7b needs about 2.7 GB of memory at Q5_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Mamba2 2.7b is a 2.83B-parameter Mamba model in GGUF format, quantized by Tedlianghk. Its trained context length is 1024K tokens. The repository has 1 quant file, from 2.0 GB (Q5_K_M) to 2.0 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M2.0 GB 2.7 GB
Fits Get file →

What GPU do you need for Mamba2 2.7b?

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: the best quant that fits is Q5_K_M (2.0 GB file, about 2.7 GB in use).

Which Mamba2 2.7b quant should you choose?

Q5_K_M (2.0 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

Architecturemamba2
Parameters2.83B
Layers64
Trained context1,048,576 tokens

Source

Quantized byTedlianghk
FamilyMamba
Licenseapache-2.0
Downloads (HF)14
Last updated2025-08-05

Frequently asked questions about Mamba2 2.7b

How much VRAM does Mamba2 2.7b need?

About 2.7 GB at Q5_K_M with an 8K context window. That is the 2.0 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 Mamba2 2.7b on an 8 GB GPU?

Yes, with Q5_K_M: the 2.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mamba2 2.7b GGUF?

It depends on the quant: Q5_K_M is 2.0 GB.

What context length does Mamba2 2.7b support?

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

Where can I download Mamba2 2.7b GGUF?

The files are on Hugging Face in the Tedlianghk/mamba2-2.7b-Q5_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mamba2 2.7b use?

Hugging Face lists the license as apache-2.0. 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 mamba2-2.7b

Similar models

Browse all →

More Mamba models

All Mamba →

Other tiny models

All tiny models →