AG

Aggregat 18.5B Q3 K M

AggregatGGUF by RedSQIDUpdated 2025-02-02
Download on Hugging Face
Parameters18.5B
Context128K
Layers63
Architecturellama
Smallest quant9.1 GB
Quick answer

Aggregat 18.5B Q3 K M needs about 11.7 GB of memory at Q3_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.5 GB.

Aggregat 18.5B Q3 K M is a 18.5B-parameter Aggregat model in GGUF format, quantized by RedSQID. Its trained context length is 128K tokens. The repository has 1 quant file, from 9.1 GB (Q3_K_M) to 9.1 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M9.1 GB 11.7 GB
Too big Get file →

What GPU do you need for Aggregat 18.5B Q3 K M?

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 Q3_K_M (9.1 GB file, about 11.7 GB in use).

Which Aggregat 18.5B Q3 K M quant should you choose?

Q3_K_M (9.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters18.5B
Layers63
Trained context131,072 tokens
KV cache (fp16)252 KB per token

Source

Quantized byRedSQID
FamilyAggregat
Downloads (HF)13
Last updated2025-02-02

Frequently asked questions about Aggregat 18.5B Q3 K M

How much VRAM does Aggregat 18.5B Q3 K M need?

About 11.7 GB at Q3_K_M with an 8K context window. That is the 9.1 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 Aggregat 18.5B Q3 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Aggregat 18.5B Q3 K M GGUF?

It depends on the quant: Q3_K_M is 9.1 GB.

What context length does Aggregat 18.5B Q3 K M support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.5 GB at 32K.

Where can I download Aggregat 18.5B Q3 K M GGUF?

The files are on Hugging Face in the RedSQID/Aggregat_18.5B-Q3_K_M-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 RedSQID

All by RedSQID →

More Aggregat models

All Aggregat →

Other medium models

All medium models →