LA

Laguna M.1

LagunaGGUF by linuxid10tUpdated 2026-06-20
Download on Hugging Face
Parameters226B
Context256K
Layers70
Architecturelaguna
Smallest quant136.1 GB
Quick answer

Laguna M.1 needs about 152.9 GB of memory at Q4_K_M (a 136.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 136.1 GB (Q4_K_M) to 451.7 GB (F16).

Laguna M.1 is a 226B-parameter Laguna model in GGUF format, quantized by linuxid10t. Its trained context length is 256K tokens. The repository has 2 quant files, from 136.1 GB (Q4_K_M) to 451.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M136.1 GB 152.9 GB
Too big Get file →
F16451.7 GB 506.4 GB
Too big Get file →

What GPU do you need for Laguna M.1?

These figures add the file size, an fp16 KV cache at an 8K context window 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 M.1 quant should you choose?

Q4_K_M is the usual starting point for Laguna M.1: it balances file size and quality well. Here it is a 136.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelaguna
Parameters226B (approximate, mixture of experts)
Layers70
Trained context262,144 tokens

Source

Quantized bylinuxid10t
FamilyLaguna
Licenseapache-2.0
Downloads (HF)50
Last updated2026-06-20

Frequently asked questions about Laguna M.1

How much VRAM does Laguna M.1 need?

About 152.9 GB at Q4_K_M with an 8K context window. That is the 136.1 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 M.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 152.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Laguna M.1 GGUF?

It depends on the quant: Q4_K_M is 136.1 GB, F16 is 451.7 GB.

What context length does Laguna M.1 support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download Laguna M.1 GGUF?

The files are on Hugging Face in the linuxid10t/Laguna-M.1-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 M.1 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-M.1

Similar models

Browse all →

More from linuxid10t

All by linuxid10t →

More Laguna models

All Laguna →

Other large models

All large models →