FR

frankenmerger delta 4b notso base

FrankenmergerGGUF by RichardErkhovUpdated 2024-10-04
Download on Hugging Face
Parameters4.67B
Context2K
Layers56
Architecturephi2
Smallest quant1.8 GB
Quick answer

frankenmerger delta 4b notso base needs about 8.1 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 1.8 GB (Q2_K) to 5.0 GB (Q8_0).

frankenmerger delta 4b notso base is a 4.67B-parameter Frankenmerger model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 22 quant files, from 1.8 GB (Q2_K) to 5.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.8 GB 3.5 GB
Fits Get file →
IQ3_XS2.0 GB 3.7 GB
Fits Get file →
Q5_K_M2.1 GB 3.7 GB
Fits Get file →
IQ3_S2.1 GB 3.7 GB
Fits Get file →
Q3_K_S2.1 GB 3.7 GB
Fits Get file →
IQ3_M2.2 GB 3.9 GB
Fits Get file →
Q3_K2.4 GB 4.0 GB
Fits Get file →
Q3_K_M2.4 GB 4.0 GB
Fits Get file →
IQ4_XS2.6 GB 4.2 GB
Fits Get file →
Q3_K_L2.6 GB 4.3 GB
Fits Get file →
Q4_02.7 GB 4.3 GB
Fits Get file →
IQ4_NL2.7 GB 4.4 GB
Fits Get file →
Q4_K_S2.7 GB 4.4 GB
Fits Get file →
Q4_K2.9 GB 4.6 GB
Fits Get file →
Q4_K_M2.9 GB 4.6 GB
Fits Get file →
Q4_13.0 GB 4.6 GB
Fits Get file →
Q5_03.2 GB 4.9 GB
Fits Get file →
Q5_K_S3.2 GB 4.9 GB
Fits Get file →
Q5_K3.4 GB 5.0 GB
Fits Get file →
Q5_13.5 GB 5.2 GB
Fits Get file →
Q6_K3.8 GB 5.5 GB
Fits Get file →
Q8_05.0 GB 6.6 GB
Fits Get file →

What GPU do you need for frankenmerger delta 4b notso base?

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 Q4_K_S (2.7 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 10.2 GB in use).

Which frankenmerger delta 4b notso base quant should you choose?

Q4_K_M is the usual starting point for frankenmerger delta 4b notso base: it balances file size and quality well. Here it is a 2.9 GB file.

The Q8_0 file is 5.0 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 1.8 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

Architecturephi2
Parameters4.67B
Layers56
Trained context2,048 tokens
KV cache (fp16)560 KB per token

Source

Quantized byRichardErkhov
Licenseapache-2.0
Downloads (HF)101
Last updated2024-10-04

Frequently asked questions about frankenmerger delta 4b notso base

How much VRAM does frankenmerger delta 4b notso base need?

About 8.1 GB at Q4_K_M with an 8K context window. That is the 2.9 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 frankenmerger delta 4b notso base on an 8 GB GPU?

Yes, with Q4_K_S: the 2.7 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 frankenmerger delta 4b notso base GGUF?

It depends on the quant: Q2_K is 1.8 GB, IQ3_XS is 2.0 GB, Q5_K_M is 2.1 GB, IQ3_S is 2.1 GB, Q3_K_S is 2.1 GB, IQ3_M is 2.2 GB and 16 more.

What context length does frankenmerger delta 4b notso base support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.7 GB at 8K and 1.2 GB at 2K.

Where can I download frankenmerger delta 4b notso base GGUF?

The files are on Hugging Face in the RichardErkhov/frankenmerger_-_delta-4b-notso-base-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 frankenmerger delta 4b notso base 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 Frankenmerger models

All Frankenmerger →

Other small models

All small models →