FA

Falcon Mamba 7b

FalconGGUF by tiiuaeUpdated 2024-10-10
Download on Hugging Face
Parameters7.27B
Context1024K
Layers64
Architecturemamba
Smallest quant4.2 GB
Quick answer

Falcon Mamba 7b needs about 5.2 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU.

Falcon Mamba 7b is a 7.27B-parameter Falcon model in GGUF format, quantized by tiiuae. Its trained context length is 1024K tokens. The repository has 1 quant file, from 4.2 GB (Q4_K_M) to 4.2 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.2 GB 5.2 GB
Fits Get file →

What GPU do you need for Falcon Mamba 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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.2 GB file, about 5.2 GB in use).

Which Falcon Mamba 7b quant should you choose?

Q4_K_M is the usual starting point for Falcon Mamba 7b: it balances file size and quality well. Here it is a 4.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemamba
Parameters7.27B
Layers64
Trained context1,048,576 tokens

Source

Quantized bytiiuae
FamilyFalcon
Licenseother
Downloads (HF)58
Last updated2024-10-10

Frequently asked questions about Falcon Mamba 7b

How much VRAM does Falcon Mamba 7b need?

About 5.2 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Falcon Mamba 7b on an 8 GB GPU?

Yes, with Q4_K_M: the 4.2 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Falcon Mamba 7b GGUF?

It depends on the quant: Q4_K_M is 4.2 GB.

What context length does Falcon Mamba 7b support?

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

Where can I download Falcon Mamba 7b GGUF?

The files are on Hugging Face in the tiiuae/falcon-mamba-7b-Q4_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 Falcon Mamba 7b use?

Hugging Face lists the license as other. 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 falcon-mamba-7b

Similar models

Browse all →

More from tiiuae

All by tiiuae →

More Falcon models

All Falcon →

Other small models

All small models →