PI

pillar 3 24625

PillarGGUF by MalcolmdenisUpdated 2025-06-24
Download on Hugging Face
Parameters23.6B
Context32K
Layers40
Architecturellama
Smallest quant14.3 GB
Quick answer

pillar 3 24625 needs about 16.2 GB of memory at its main file (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

pillar 3 24625 is a 23.6B-parameter Pillar model in GGUF format, quantized by Malcolmdenis. Its trained context length is 32K tokens. The repository has 1 quant file, from 14.3 GB to 14.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—14.3 GB 16.2 GB
Too big Get file →

What GPU do you need for pillar 3 24625?

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: the best quant that fits is the main file (14.3 GB file, about 16.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byMalcolmdenis
FamilyPillar
Licensecc-by-4.0
Downloads (HF)6
Last updated2025-06-24

Frequently asked questions about pillar 3 24625

How much VRAM does pillar 3 24625 need?

About 16.2 GB at its main file with an 8K context window. That is the 14.3 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 pillar 3 24625 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of pillar 3 24625 GGUF?

It depends on the quant: file is 14.3 GB.

What context length does pillar 3 24625 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download pillar 3 24625 GGUF?

The files are on Hugging Face in the Malcolmdenis/pillar-3-24625 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does pillar 3 24625 use?

Hugging Face lists the license as cc-by-4.0. 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 Malcolmdenis

All by Malcolmdenis →

More Pillar models

All Pillar →

Other medium models

All medium models →