Laguna S 2.1 Heretic needs about 73.3 GB of memory at Q4_K_M (a 71.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.4 GB to 96.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Laguna S 2.1 Heretic – a 118 billion‑parameter Llama‑style model
Laguna S 2.1 Heretic is a 118 billion‑parameter model from the Laguna family. It supports a context length of 1 048 576 tokens and is released under the openmdw‑1.1 license. The model is a mixture of experts with no vision capability.
Good at
- Large‑context text generation
- Complex reasoning
- Long‑form dialogue
Limits
- No vision support
- Requires large VRAM for full precision
- License is openmdw‑1.1
Best for
- Research prototypes
- Enterprise chatbots
- Content creation pipelines
Who it’s for. Developers and researchers who need a high‑capacity language model with extended context. The model is suitable for teams that can provision sufficient GPU memory and comply with the openmdw‑1.1 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 2.5 GB | Fits | Get file → | |
| IQ1_S | 23.8 GB | 25.9 GB | Too big | Get file → | |
| IQ1_M | 26.4 GB | 28.5 GB | Too big | Get file → | |
| IQ2_XXS | 30.8 GB | 32.9 GB | Too big | Get file → | |
| IQ2_XS | 34.4 GB | 36.5 GB | Too big | Get file → | |
| IQ2_S | 34.9 GB | 37.0 GB | Too big | Get file → | |
| IQ2_M | 38.4 GB | 40.5 GB | Too big | Get file → | |
| Q2_K_S | 39.9 GB | 42.0 GB | Too big | Get file → | |
| Q2_K | 42.9 GB | 45.0 GB | Too big | Get file → | |
| IQ3_XXS | 45.2 GB | 47.4 GB | Too big | Get file → | |
| IQ3_XS | 48.0 GB | 50.1 GB | Too big | Get file → | |
| Q3_K_S | 50.8 GB | 52.9 GB | Too big | Get file → | |
| IQ3_S | 50.8 GB | 52.9 GB | Too big | Get file → | |
| IQ3_M | 51.5 GB | 53.6 GB | Too big | Get file → | |
| Q3_K_M | 56.2 GB | 58.3 GB | Too big | Get file → | |
| Q3_K_L | 60.9 GB | 63.0 GB | Too big | Get file → | |
| IQ4_XS | 62.7 GB | 64.8 GB | Too big | Get file → | |
| Q4_0 | 66.6 GB | 68.7 GB | Too big | Get file → | |
| Q4_K_S | 66.9 GB | 69.0 GB | Too big | Get file → | |
| Q4_K_M | 71.2 GB | 73.3 GB | Too big | Get file → | |
| Q4_1 | 73.7 GB | 75.8 GB | Too big | Get file → | |
| Q5_K_S | 81.0 GB | 83.1 GB | Too big | Get file → | |
| Q5_K_M | 83.5 GB | 85.6 GB | Too big | Get file → | |
| Q6_K | 96.6 GB | 98.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (23.76 GB file, 25.9 GB memory at 8 k context). For 12 GB VRAM, IQ1_M (26.41 GB file, 28.5 GB memory). For 16 GB VRAM, IQ2_XS (34.4 GB file, 36.5 GB memory). Estimates are approximate.
What GPU do you need for Laguna S 2.1 Heretic?
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 (26.4 GB file, about 28.5 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_XXS (45.2 GB file, about 47.4 GB in use).
Which Laguna S 2.1 Heretic quant should you choose?
Q4_K_M is the usual starting point for Laguna S 2.1 Heretic: it balances file size and quality well. Here it is a 71.2 GB file.
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
Source
Frequently asked questions about Laguna S 2.1 Heretic
How much VRAM does Laguna S 2.1 Heretic need?
About 73.3 GB at Q4_K_M with an 8K context window. That is the 71.2 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 Heretic 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 Heretic GGUF?
It depends on the quant: file is 0.4 GB, IQ1_S is 23.8 GB, IQ1_M is 26.4 GB, IQ2_XXS is 30.8 GB, IQ2_XS is 34.4 GB, IQ2_S is 34.9 GB and 18 more.
What context length does Laguna S 2.1 Heretic 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 Heretic GGUF?
The files are on Hugging Face in the mradermacher/Laguna-S-2.1-Heretic-i1-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 Heretic 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 Heretic on 8 GB VRAM?
Use the IQ1_S quant, which requires about 25.9 GB of VRAM at 8 k context. 8 GB VRAM is insufficient for full precision or larger quants.
What license applies to this model?
The model is released under the openmdw‑1.1 license.
Does this model support image input?
No, Laguna S 2.1 Heretic does not have vision capability.