LA

Laguna-S-2.1

LagunaGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters118B
Context1024K
Layers48
Architecturelaguna
Smallest quant67.7 GB
Quick answer

Laguna-S-2.1 needs about 69.8 GB of memory at Q4_K_M (a 67.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 67.7 GB (Q4_K_M) to 125.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Laguna‑S‑2.1, a 118B Mixture‑of‑Experts LLM for long‑horizon reasoning

Laguna‑S‑2.1 is a 118B total‑parameter Mixture‑of‑Experts model with 8B activated parameters per token. It offers a 1,048,576‑token context window and native reasoning support with interleaved thinking. The model is released under the fully permissive OpenMDW‑1.1 license.

Good at

  • Long‑horizon reasoning
  • Agentic coding
  • Tool‑aware interleaved thinking

Limits

  • 1,048,576‑token context only
  • Requires >69.8 GB VRAM for Q4_K_M
  • No vision support

Best for

  • Complex coding tasks
  • Multi‑step problem solving
  • Tool‑integrated workflows

Who it’s for. Developers building agentic applications that need deep reasoning and long context. The model is suitable for commercial use under the OpenMDW‑1.1 license, allowing modification and deployment without permission.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M67.7 GB 69.8 GB
Too big Get file →
Q8_0125.0 GB 127.1 GB
Too big Get file →

For a 8 GB VRAM budget, the Q4_K_M quantization is the smallest available, but it still requires approximately 69.8 GB VRAM at 8 k context. The Q8_0 variant needs about 127.1 GB VRAM. Choose the smallest quant if memory is limited.

What GPU do you need for Laguna-S-2.1?

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-S-2.1 quant should you choose?

Q4_K_M is the usual starting point for Laguna-S-2.1: it balances file size and quality well. Here it is a 67.7 GB file.

The Q8_0 file is 125.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelaguna
Parameters118B (approximate, mixture of experts)
Layers48
Trained context1,048,576 tokens
KV cache (fp16)192 KB per token

Source

Quantized byggml-org
FamilyLaguna
Downloads (HF)826
Last updated2026-10-19

Frequently asked questions about Laguna-S-2.1

How much VRAM does Laguna-S-2.1 need?

About 69.8 GB at Q4_K_M with an 8K context window. That is the 67.7 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-S-2.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 69.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Laguna-S-2.1 GGUF?

It depends on the quant: Q4_K_M is 67.7 GB, Q8_0 is 125.0 GB.

What context length does Laguna-S-2.1 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Laguna-S-2.1 GGUF?

The files are on Hugging Face in the ggml-org/Laguna-S-2.1-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-S-2.1 use?

Hugging Face lists the license as openmdw-1.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Laguna‑S‑2.1 on 8 GB VRAM?

No. The smallest quant (Q4_K_M) needs about 69.8 GB VRAM at 8 k context, and Q8_0 needs about 127.1 GB.

Does Laguna‑S‑2.1 support vision?

No, the model is text‑to‑text only.

Other GGUFs of Laguna-S-2.1

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Laguna models

All Laguna →

Other large models

All large models →