LA

Laguna S 2.1 APEX

LagunaGGUF by MyricUpdated 2026-10-24
Download on Hugging Face
Parameters118B
Context1024K
Layers6
Architecturedflash
Smallest quant0.7 GB
Quick answer

Laguna S 2.1 APEX needs about 48.6 GB of memory at its main file (a 47.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 0.7 GB (Q4_K) to 74.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.

Laguna S 2.1 APEX – 118B parameter MoE model for agentic coding

Laguna S 2.1 APEX is a 118B total parameter Mixture-of-Experts model with ~8B activated per token. It supports a 1,048,576-token context window and interleaved reasoning with tool calls. The model is released under the openmdw-1.1 license.

Good at

  • Agentic coding
  • Long-horizon reasoning
  • Tool integration

Limits

  • No vision support
  • Large memory requirement for full precision
  • Requires llama.cpp fork for DFlash

Best for

  • Complex coding tasks
  • Multi-step reasoning workflows
  • Tool-assisted generation

Who it’s for. Developers and researchers needing a large MoE model for text‑to‑text tasks that require extensive context and reasoning. The model is suitable for local deployment with sufficient VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.7 GB 1.4 GB
Fits Get file →
Q8_01.2 GB 1.9 GB
Fits Get file →
—43.6 GB 44.3 GB
Too big Get file →
—43.7 GB 44.4 GB
Too big Get file →
—47.9 GB 48.6 GB
Too big Get file →
—47.9 GB 48.6 GB
Too big Get file →
—54.4 GB 55.1 GB
Too big Get file →
—54.4 GB 55.1 GB
Too big Get file →
—73.9 GB 74.6 GB
Too big Get file →
—74.0 GB 74.7 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K GGUF file (0.65 GB, ~1.4 GB memory at 8 k context). For 16 GB VRAM, the Q8_0 file (1.19 GB, ~1.9 GB memory) is recommended. Larger memory budgets can use the full‑precision files if available.

What GPU do you need for Laguna S 2.1 APEX?

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: the best quant that fits is Q8_0 (1.2 GB file, about 1.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (1.2 GB file, about 1.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (1.2 GB file, about 1.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (1.2 GB file, about 1.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (1.2 GB file, about 1.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (1.2 GB file, about 1.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (1.2 GB file, about 1.9 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (43.7 GB file, about 44.4 GB in use).

Which Laguna S 2.1 APEX quant should you choose?

If memory is tight, the smallest file is Q4_K at 0.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters118B
Layers6
Trained context1,048,576 tokens
KV cache (fp16)24 KB per token

Source

Quantized byMyric
FamilyLaguna
Downloads (HF)173,338
Last updated2026-10-24

Frequently asked questions about Laguna S 2.1 APEX

How much VRAM does Laguna S 2.1 APEX need?

About 48.6 GB at its main file with an 8K context window. That is the 47.9 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 APEX on an 8 GB GPU?

Yes, with Q8_0: the 1.2 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q4_K is 0.7 GB, Q8_0 is 1.2 GB, file is 43.6 GB, file is 43.7 GB, file is 47.9 GB, file is 47.9 GB and 4 more.

What context length does Laguna S 2.1 APEX 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 0.2 GB at 8K and 0.8 GB at 32K.

Where can I download Laguna S 2.1 APEX GGUF?

The files are on Hugging Face in the Myric/Laguna-S-2.1-APEX-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 APEX 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 APEX on 8 GB VRAM?

Yes, using the Q4_K quantized GGUF file which requires about 1.4 GB VRAM at 8 k context.

Does the model support image input?

No, the model is text‑to‑text only.

What license applies to this model?

The model is released under the openmdw-1.1 license, which allows free use, modification, and commercial deployment.

Other GGUFs of Laguna-S-2.1

Similar models

Browse all →

More from Myric

All by Myric →

More Laguna models

All Laguna →

Other large models

All large models →