LA

Laguna XS.2

LagunaGGUF by poolside-laguna-hackathonUpdated 2026-05-30
Download on Hugging Face
Parameters33.4B
Context128K
Layers40
Architectureqwen2moe
Smallest quant64.1 GB
Quick answer

Laguna XS.2 needs about 65.9 GB of memory at Q4_K_M (a 64.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 64.1 GB (Q4_K_M) to 66.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Laguna XS.2 is a 33.4B-parameter Laguna model in GGUF format, quantized by poolside-laguna-hackathon. Its trained context length is 128K tokens. The repository has 2 quant files, from 64.1 GB (Q4_K_M) to 66.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M64.1 GB 65.9 GB
Too big Get file →
F1666.9 GB 68.8 GB
Too big Get file →

What GPU do you need for Laguna XS.2?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Laguna XS.2 quant should you choose?

Q4_K_M is the usual starting point for Laguna XS.2: it balances file size and quality well. Here it is a 64.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2moe
Parameters33.4B (approximate, mixture of experts)
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

FamilyLaguna
Licenseapache-2.0
Downloads (HF)196
Last updated2026-05-30

Frequently asked questions about Laguna XS.2

How much VRAM does Laguna XS.2 need?

About 65.9 GB at Q4_K_M with an 8K context window. That is the 64.1 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 Laguna XS.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 65.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Laguna XS.2 GGUF?

It depends on the quant: Q4_K_M is 64.1 GB, F16 is 66.9 GB.

What context length does Laguna XS.2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Laguna XS.2 GGUF?

The files are on Hugging Face in the poolside-laguna-hackathon/Laguna-XS.2-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 Laguna XS.2 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.

Other GGUFs of Laguna-XS.2

Similar models

Browse all →

More from poolside-laguna-hackathon

All by poolside-laguna-hackathon →

More Laguna models

All Laguna →

Other medium models

All medium models →