LY

Lyra

LyraGGUF by AMBNNJUpdated 2025-12-31
Download on Hugging Face
Parameters3.88B
Context128K
Layers34
Architecturegemma3
Smallest quant2.5 GB
Quick answer

Lyra needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

Lyra is a 3.88B-parameter Lyra model in GGUF format, quantized by AMBNNJ. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.5 GB (Q4_K_M) to 2.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.1 GB
Fits Get file →

What GPU do you need for Lyra?

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: the best quant that fits is Q4_K_M (2.5 GB file, about 4.1 GB in use).

Which Lyra quant should you choose?

Q4_K_M is the usual starting point for Lyra: it balances file size and quality well. Here it is a 2.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters3.88B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

Quantized byAMBNNJ
FamilyLyra
RepositoryAMBNNJ/Lyra
Licenseapache-2.0
Downloads (HF)7
Last updated2025-12-31

Frequently asked questions about Lyra

How much VRAM does Lyra need?

About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Lyra on an 8 GB GPU?

Yes, with Q4_K_M: the 2.5 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Lyra GGUF?

It depends on the quant: Q4_K_M is 2.5 GB.

What context length does Lyra support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download Lyra GGUF?

The files are on Hugging Face in the AMBNNJ/Lyra repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Lyra 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 Lyra models

All Lyra →

Other small models

All small models →