DI

.\DigitalSoul

DigitalsoulGGUF by mradermacherUpdated 2024-11-18
Download on Hugging Face
Parameters4.62B
Context128K
Layers42
Architecturellama
Smallest quant1.2 GB
Quick answer

.\DigitalSoul needs about 4.8 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.2 GB (IQ1_S) to 3.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

.\DigitalSoul is a 4.62B-parameter Digitalsoul model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 24 quant files, from 1.2 GB (IQ1_S) to 3.8 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.2 GB 3.1 GB
Fits Get file →
IQ1_M1.2 GB 3.2 GB
Fits Get file →
IQ2_XXS1.4 GB 3.3 GB
Fits Get file →
IQ2_XS1.5 GB 3.4 GB
Fits Get file →
IQ2_S1.6 GB 3.5 GB
Fits Get file →
IQ2_M1.7 GB 3.6 GB
Fits Get file →
Q2_K1.9 GB 3.8 GB
Fits Get file →
IQ3_XXS1.9 GB 3.8 GB
Fits Get file →
IQ3_XS2.1 GB 4.0 GB
Fits Get file →
IQ3_S2.1 GB 4.1 GB
Fits Get file →
Q3_K_S2.1 GB 4.1 GB
Fits Get file →
IQ3_M2.2 GB 4.1 GB
Fits Get file →
Q3_K_M2.4 GB 4.3 GB
Fits Get file →
Q3_K_L2.6 GB 4.5 GB
Fits Get file →
IQ4_XS2.6 GB 4.5 GB
Fits Get file →
Q4_02.7 GB 4.6 GB
Fits Get file →
Q4_02.7 GB 4.6 GB
Fits Get file →
Q4_02.7 GB 4.6 GB
Fits Get file →
Q4_02.7 GB 4.6 GB
Fits Get file →
Q4_K_S2.7 GB 4.6 GB
Fits Get file →
Q4_K_M2.9 GB 4.8 GB
Fits Get file →
Q5_K_S3.2 GB 5.1 GB
Fits Get file →
Q5_K_M3.3 GB 5.2 GB
Fits Get file →
Q6_K3.8 GB 5.7 GB
Fits Get file →

What GPU do you need for .\DigitalSoul?

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 IQ3_XS (2.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.8 GB file, about 5.7 GB in use).

Which .\DigitalSoul quant should you choose?

Q4_K_M is the usual starting point for .\DigitalSoul: it balances file size and quality well. Here it is a 2.9 GB file.

If memory is tight, the smallest file is IQ1_S at 1.2 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

Architecturellama
Parameters4.62B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized bymradermacher
Downloads (HF)117
Last updated2024-11-18

Frequently asked questions about .\DigitalSoul

How much VRAM does .\DigitalSoul need?

About 4.8 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 .\DigitalSoul on an 8 GB GPU?

Yes, with Q6_K: the 3.8 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of .\DigitalSoul GGUF?

It depends on the quant: IQ1_S is 1.2 GB, IQ1_M is 1.2 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.6 GB, IQ2_M is 1.7 GB and 18 more.

What context length does .\DigitalSoul support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download .\DigitalSoul GGUF?

The files are on Hugging Face in the mradermacher/DigitalSoul-4B-i1-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 .\DigitalSoul use?

Hugging Face lists the license as artistic-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of DigitalSoul-4B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Digitalsoul models

All Digitalsoul →

Other small models

All small models →