LA

Laguna S 2.1

LagunaGGUF by bartowskiUpdated 2026-07-22
Download on Hugging Face
Parameters118B
Context1024K
Layers48
Architecturelaguna
Smallest quant0.4 GB
Quick answer

Laguna S 2.1 needs about 73.9 GB of memory at Q4_K_M (a 71.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 29 quants, from 0.4 GB to 235.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

118B Mixture‑of‑Experts model for long‑horizon coding

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

Good at

  • Long‑horizon coding
  • Agentic reasoning
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is permissive but no commercial support

Best for

  • Code generation with tool calls
  • Complex reasoning tasks
  • Large‑scale text analysis

Who it’s for. Developers and researchers needing a high‑capacity language model for coding and reasoning. The model is suitable for commercial and non‑commercial projects under the OpenMDW‑1.1 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 2.5 GB
Fits Get file →
IQ1_S24.9 GB 27.0 GB
Too big Get file →
IQ1_M27.6 GB 29.8 GB
Too big Get file →
IQ2_XXS32.0 GB 34.1 GB
Too big Get file →
IQ2_XS35.6 GB 37.7 GB
Too big Get file →
IQ2_S36.3 GB 38.4 GB
Too big Get file →
IQ2_M39.9 GB 42.0 GB
Too big Get file →
Q2_K41.8 GB 43.9 GB
Too big Get file →
Q2_K_L42.1 GB 44.2 GB
Too big Get file →
IQ3_XXS49.5 GB 51.6 GB
Too big Get file →
Q3_K_S51.6 GB 53.7 GB
Too big Get file →
IQ3_XS54.0 GB (2 parts) 56.1 GB
Too big Get file →
Q3_K_M54.0 GB (2 parts) 56.1 GB
Too big Get file →
Q3_K_L56.2 GB (2 parts) 58.3 GB
Too big Get file →
Q3_K_XL56.5 GB (2 parts) 58.6 GB
Too big Get file →
IQ3_M56.5 GB (2 parts) 58.6 GB
Too big Get file →
IQ4_XS63.3 GB (2 parts) 65.4 GB
Too big Get file →
IQ4_NL66.9 GB (2 parts) 69.0 GB
Too big Get file →
Q4_067.0 GB (2 parts) 69.2 GB
Too big Get file →
Q4_K_S69.1 GB (2 parts) 71.2 GB
Too big Get file →
Q4_K_M71.8 GB (2 parts) 73.9 GB
Too big Get file →
Q4_174.0 GB (2 parts) 76.2 GB
Too big Get file →
Q5_K_S81.3 GB (3 parts) 83.4 GB
Too big Get file →
Q5_K_M84.0 GB (3 parts) 86.1 GB
Too big Get file →
Q5_K_L84.2 GB (3 parts) 86.3 GB
Too big Get file →
Q6_K101.7 GB (3 parts) 103.8 GB
Too big Get file →
Q6_K_L101.8 GB (3 parts) 103.9 GB
Too big Get file →
Q8_0125.0 GB (4 parts) 127.1 GB
Too big Get file →
BF16235.2 GB (7 parts) 237.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (24.86 GB file, 27 GB memory at 8 k context). For 16 GB VRAM, IQ2_M (39.93 GB file, 42 GB memory). For 32 GB VRAM, Q4_K_M (71.76 GB file, 73.9 GB memory). Estimates are approximate.

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: the best quant that fits is the main file (0.4 GB file, about 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 2.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 2.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 2.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 2.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 2.5 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ1_M (27.6 GB file, about 29.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q2_K_L (42.1 GB file, about 44.2 GB in use).

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 71.8 GB file.

The Q8_0 file is 125.0 GB, about 1.7 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.

If memory is tight, the smallest file is the first one in the table at 0.4 GB, with the quality trade-offs that come with fewer bits.

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 bybartowski
FamilyLaguna
Downloads (HF)1,840
Last updated2026-07-22

Frequently asked questions about Laguna S 2.1

How much VRAM does Laguna S 2.1 need?

About 73.9 GB at Q4_K_M with an 8K context window. That is the 71.8 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?

Yes, with the smaller files: the 0.4 GB file needs about 2.5 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 GGUF?

It depends on the quant: file is 0.4 GB, IQ1_S is 24.9 GB, IQ1_M is 27.6 GB, IQ2_XXS is 32.0 GB, IQ2_XS is 35.6 GB, IQ2_S is 36.3 GB and 23 more.

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 bartowski/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?

Use the IQ1_S quant, which requires about 27 GB memory at 8 k context, so 8 GB VRAM is insufficient for full inference.

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 bartowski

All by bartowski →

More Laguna models

All Laguna →

Other large models

All large models →