FA

ssmits Falcon2 5.5B Dutch

FalconGGUF by RichardErkhovUpdated 2024-11-01
Download on Hugging Face
Parameters5.47B
Context2K
Layers28
Architecturefalcon
Smallest quant2.2 GB
Quick answer

ssmits Falcon2 5.5B Dutch needs about 4.9 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 19 quants, from 2.2 GB (Q2_K) to 5.8 GB (Q8_0).

ssmits Falcon2 5.5B Dutch is a 5.47B-parameter Falcon model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 19 quant files, from 2.2 GB (Q2_K) to 5.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.2 GB 2.9 GB
Fits Get file →
Q3_K_S2.5 GB 3.3 GB
Fits Get file →
Q3_K2.7 GB 3.5 GB
Fits Get file →
Q3_K_M2.7 GB 3.5 GB
Fits Get file →
Q3_K_L2.9 GB 3.7 GB
Fits Get file →
IQ4_XS3.1 GB 3.8 GB
Fits Get file →
Q4_03.2 GB 3.9 GB
Fits Get file →
Q4_K_S3.2 GB 3.9 GB
Fits Get file →
IQ4_NL3.2 GB 4.0 GB
Fits Get file →
Q4_K3.4 GB 4.2 GB
Fits Get file →
Q4_K_M3.4 GB 4.2 GB
Fits Get file →
Q4_13.5 GB 4.3 GB
Fits Get file →
Q5_03.9 GB 4.6 GB
Fits Get file →
Q5_K_S3.9 GB 4.6 GB
Fits Get file →
Q5_K4.1 GB 4.8 GB
Fits Get file →
Q5_K_M4.1 GB 4.8 GB
Fits Get file →
Q5_14.2 GB 4.9 GB
Fits Get file →
Q6_K4.6 GB 5.3 GB
Fits Get file →
Q8_05.8 GB 6.5 GB
Fits Get file →

What GPU do you need for ssmits Falcon2 5.5B Dutch?

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: the best quant that fits is Q3_K_S (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (4.6 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.8 GB file, about 7.2 GB in use).

Which ssmits Falcon2 5.5B Dutch quant should you choose?

Q4_K_M is the usual starting point for ssmits Falcon2 5.5B Dutch: it balances file size and quality well. Here it is a 3.4 GB file.

The Q8_0 file is 5.8 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 2.2 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
Parameters5.47B
Layers28
Trained context2,048 tokens
KV cache (fp16)112 KB per token

Source

Quantized byRichardErkhov
FamilyFalcon
Licenseapache-2.0
Downloads (HF)317
Last updated2024-11-01

Frequently asked questions about ssmits Falcon2 5.5B Dutch

How much VRAM does ssmits Falcon2 5.5B Dutch need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 3.4 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 ssmits Falcon2 5.5B Dutch on an 8 GB GPU?

Yes, with Q8_0: the 5.8 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ssmits Falcon2 5.5B Dutch GGUF?

It depends on the quant: Q2_K is 2.2 GB, Q3_K_S is 2.5 GB, Q3_K is 2.7 GB, Q3_K_M is 2.7 GB, Q3_K_L is 2.9 GB, IQ4_XS is 3.1 GB and 13 more.

What context length does ssmits Falcon2 5.5B Dutch support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.2 GB at 2K.

Where can I download ssmits Falcon2 5.5B Dutch GGUF?

The files are on Hugging Face in the RichardErkhov/ssmits_-_Falcon2-5.5B-Dutch-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 ssmits Falcon2 5.5B Dutch 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 RichardErkhov

All by RichardErkhov →

More Falcon models

All Falcon →

Other small models

All small models →