FA

Falcon

FalconGGUF by maddes8chtUpdated 2026-06-09
Download on Hugging Face
Parameters41.9B
Context2K
Layers60
Architecturefalcon
Smallest quant23.9 GB
Quick answer

Falcon needs about 32.2 GB of memory at BF16 (a 30.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 23.9 GB (BF16) to 44.6 GB (BF16).

Falcon is a 41.9B-parameter Falcon model in GGUF format, quantized by maddes8cht. Its trained context length is 2K tokens. The repository has 5 quant files, from 23.9 GB (BF16) to 44.6 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1623.9 GB 24.6 GB
Too big Get file →
BF1625.5 GB 26.3 GB
Too big Get file →
BF1630.7 GB 31.5 GB
Too big Get file →
BF1634.5 GB 35.3 GB
Too big Get file →
BF1644.6 GB 45.3 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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is BF16 (25.5 GB file, about 27.0 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (44.6 GB file, about 46.1 GB in use).

Which Falcon quant should you choose?

BF16 (30.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is BF16 at 23.9 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturefalcon
Parameters41.9B
Layers60
Trained context2,048 tokens
KV cache (fp16)120 KB per token

Source

Quantized bymaddes8cht
FamilyFalcon
Licenseapache-2.0
Downloads (HF)116
Last updated2026-06-09

Frequently asked questions about Falcon

How much VRAM does Falcon need?

About 32.2 GB at BF16 with an 8K context window. That is the 30.7 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 25.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Falcon GGUF?

It depends on the quant: BF16 is 23.9 GB, BF16 is 25.5 GB, BF16 is 30.7 GB, BF16 is 34.5 GB, BF16 is 44.6 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 1.0 GB at 8K and 0.3 GB at 2K.

Where can I download Falcon GGUF?

The files are on Hugging Face in the maddes8cht/OpenBuddy-openbuddy-falcon-40b-v9-bf16-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 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.

Similar models

Browse all →

More from maddes8cht

All by maddes8cht →

More Falcon models

All Falcon →

Other large models

All large models →