FA

Falcon

FalconGGUF by LiteLLMsUpdated 2024-05-24
Download on Hugging Face
Parameters11.1B
Context2K
Layers60
Architecturefalcon
Smallest quant4.3 GB
Quick answer

Falcon needs about 9.4 GB of memory at Q4_K_M (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.3 GB (Q2_K) to 11.8 GB (Q8_0).

Falcon is a 11.1B-parameter Falcon model in GGUF format, quantized by LiteLLMs. Its trained context length is 2K tokens. The repository has 14 quant files, from 4.3 GB (Q2_K) to 11.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.3 GB 5.3 GB
Fits Get file →
Q3_K_S4.9 GB 5.9 GB
Fits Get file →
Q3_K_M5.4 GB 6.4 GB
Fits Get file →
Q3_K_L5.8 GB 6.8 GB
Fits Get file →
Q4_06.4 GB 7.4 GB
Tight Get file →
Q4_K_S6.4 GB 7.4 GB
Tight Get file →
Q4_K_M6.8 GB 7.9 GB
Tight Get file →
Q4_17.1 GB 8.1 GB
Too big Get file →
Q5_07.7 GB 8.7 GB
Too big Get file →
Q5_K_S7.7 GB 8.7 GB
Too big Get file →
Q5_K_M8.2 GB 9.2 GB
Too big Get file →
Q5_18.4 GB 9.4 GB
Too big Get file →
Q6_K9.2 GB 10.2 GB
Too big Get file →
Q8_011.8 GB 12.8 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: the best quant that fits is Q3_K_M (5.4 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (9.2 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.8 GB file, about 14.3 GB in use).

Which Falcon quant should you choose?

Q4_K_M is the usual starting point for Falcon: it balances file size and quality well. Here it is a 6.8 GB file.

The Q8_0 file is 11.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 4.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byLiteLLMs
FamilyFalcon
Licenseunknown
Downloads (HF)75
Last updated2024-05-24

Frequently asked questions about Falcon

How much VRAM does Falcon need?

About 9.4 GB at Q4_K_M with an 8K context window. That is the 6.8 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 Falcon on an 8 GB GPU?

Yes, with Q3_K_M: the 5.4 GB file needs about 7.9 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: Q2_K is 4.3 GB, Q3_K_S is 4.9 GB, Q3_K_M is 5.4 GB, Q3_K_L is 5.8 GB, Q4_0 is 6.4 GB, Q4_K_S is 6.4 GB and 8 more.

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 LiteLLMs/falcon-11B-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.

Similar models

Browse all →

More from LiteLLMs

All by LiteLLMs →

More Falcon models

All Falcon →

Other medium models

All medium models →