FA

Falcon

FalconGGUF by rzabounidisUpdated 2024-06-08
Download on Hugging Face
Parameters11.1B
Context2K
Layers60
Architecturefalcon
Smallest quant9.2 GB
Quick answer

Falcon needs about 11.7 GB of memory at Q6_K (a 9.2 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Falcon is a 11.1B-parameter Falcon model in GGUF format, quantized by rzabounidis. Its trained context length is 2K tokens. The repository has 1 quant file, from 9.2 GB (Q6_K) to 9.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K9.2 GB 10.2 GB
Too big 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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q6_K (9.2 GB file, about 11.7 GB in use).

Which Falcon quant should you choose?

Q6_K (9.2 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturefalcon
Parameters11.1B
Layers60
Trained context2,048 tokens
KV cache (fp16)240 KB per token

Source

Quantized byrzabounidis
FamilyFalcon
Licenseunknown
Downloads (HF)7
Last updated2024-06-08

Frequently asked questions about Falcon

How much VRAM does Falcon need?

About 11.7 GB at Q6_K with an 8K context window. That is the 9.2 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?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Falcon GGUF?

It depends on the quant: Q6_K is 9.2 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 2.0 GB at 8K and 0.5 GB at 2K.

Where can I download Falcon GGUF?

The files are on Hugging Face in the rzabounidis/falcon-11B-Q6_K-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 use?

Hugging Face lists the license as unknown. 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-11B

Similar models

Browse all →

More Falcon models

All Falcon →

Other medium models

All medium models →