FA

Falcon2 8B Italian Q8 0

FalconGGUF by lukecageUpdated 2024-08-29
Download on Hugging Face
Parameters8.11B
Context2K
Layers43
Architecturefalcon
Smallest quant8.6 GB
Quick answer

Falcon2 8B Italian Q8 0 needs about 10.6 GB of memory at Q8_0 (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Falcon2 8B Italian Q8 0 is a 8.11B-parameter Falcon model in GGUF format, quantized by lukecage. Its trained context length is 2K tokens. The repository has 1 quant file, from 8.6 GB (Q8_0) to 8.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.6 GB 9.5 GB
Too big Get file →

What GPU do you need for Falcon2 8B Italian Q8 0?

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 Q8_0 (8.6 GB file, about 10.6 GB in use).

Which Falcon2 8B Italian Q8 0 quant should you choose?

Q8_0 (8.6 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
Parameters8.11B
Layers43
Trained context2,048 tokens
KV cache (fp16)172 KB per token

Source

Quantized bylukecage
FamilyFalcon
Downloads (HF)6
Last updated2024-08-29

Frequently asked questions about Falcon2 8B Italian Q8 0

How much VRAM does Falcon2 8B Italian Q8 0 need?

About 10.6 GB at Q8_0 with an 8K context window. That is the 8.6 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 Falcon2 8B Italian Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Falcon2 8B Italian Q8 0 GGUF?

It depends on the quant: Q8_0 is 8.6 GB.

What context length does Falcon2 8B Italian Q8 0 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.4 GB at 8K and 0.4 GB at 2K.

Where can I download Falcon2 8B Italian Q8 0 GGUF?

The files are on Hugging Face in the lukecage/Falcon2-8B-Italian-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from lukecage

All by lukecage →

More Falcon models

All Falcon →

Other small models

All small models →