FA

Falcon

FalconGGUF by NikolayKozloffUpdated 2024-05-20
Download on Hugging Face
Parameters4.94B
Context2K
Layers25
Architecturefalcon
Smallest quant5.2 GB
Quick answer

Falcon needs about 6.6 GB of memory at Q8_0 (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU.

Falcon is a 4.94B-parameter Falcon model in GGUF format, quantized by NikolayKozloff. Its trained context length is 2K tokens. The repository has 1 quant file, from 5.2 GB (Q8_0) to 5.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_05.2 GB 6.0 GB
Fits Get file →

What GPU do you need for Falcon?

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: the best quant that fits is Q8_0 (5.2 GB file, about 6.6 GB in use).

Which Falcon quant should you choose?

Q8_0 (5.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturefalcon
Parameters4.94B
Layers25
Trained context2,048 tokens
KV cache (fp16)100 KB per token

Source

Quantized byNikolayKozloff
FamilyFalcon
Downloads (HF)22
Last updated2024-05-20

Frequently asked questions about Falcon

How much VRAM does Falcon need?

About 6.6 GB at Q8_0 with an 8K context window. That is the 5.2 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 on an 8 GB GPU?

Yes, with Q8_0: the 5.2 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Falcon GGUF?

It depends on the quant: Q8_0 is 5.2 GB.

What context length does Falcon support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.2 GB at 2K.

Where can I download Falcon GGUF?

The files are on Hugging Face in the NikolayKozloff/Falcon2-5.5B-Swedish-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of falcon-11B

Similar models

Browse all →

More from NikolayKozloff

All by NikolayKozloff →

More Falcon models

All Falcon →

Other small models

All small models →