Laguna S 2.1 Uncensored Heretic needs about 75.1 GB of memory at Q4_K_M (a 73.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 49.2 GB (Q2_K) to 235.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Laguna S 2.1 Uncensored Heretic – 118B Mixture‑of‑Experts model with vision support
Laguna S 2.1 Uncensored Heretic is a 118B parameter Mixture‑of‑Experts model. It offers a 1,048,576‑token context window and experimental vision capabilities. The model is released under the openmdw-1.1 license.
Good at
- Long‑horizon reasoning
- Agentic coding
- Vision‑enabled multimodal tasks
Limits
- Requires a vision projector file for vision use
- Large VRAM needed for higher quants
- No official GPU acceleration beyond llama.cpp
Best for
- Complex coding assistants
- Large‑scale document analysis
- Multimodal content generation
Who it’s for. Developers and researchers needing a large, uncensored language model with extended context and optional vision. The model is suitable for advanced AI applications that require deep reasoning and multimodal input.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 49.2 GB | 51.3 GB | Too big | Get file → | |
| Q3_K_S | 56.9 GB | 59.0 GB | Too big | Get file → | |
| Q3_K_M | 62.3 GB | 64.4 GB | Too big | Get file → | |
| Q3_K_L | 66.8 GB | 68.9 GB | Too big | Get file → | |
| Q4_K_S | 72.7 GB | 74.8 GB | Too big | Get file → | |
| Q4_K_M | 73.0 GB | 75.1 GB | Too big | Get file → | |
| Q5_K_M | 84.9 GB | 87.0 GB | Too big | Get file → | |
| Q5_K_S | 86.3 GB | 88.4 GB | Too big | Get file → | |
| Q6_K | 97.5 GB | 99.6 GB | Too big | Get file → | |
| Q8_0 | 128.8 GB | 130.9 GB | Too big | Get file → | |
| BF16 | 235.2 GB (2 parts) | 237.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (file size 72.69 GB, memory 74.8 GB at 8 k context). For 16 GB VRAM, Q5_K_M (84.91 GB, 87 GB). For 32 GB VRAM, Q6_K (97.53 GB, 99.6 GB). Memory estimates are approximate.
What GPU do you need for Laguna S 2.1 Uncensored 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: 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 Uncensored Heretic quant should you choose?
Q4_K_M is the usual starting point for Laguna S 2.1 Uncensored Heretic: it balances file size and quality well. Here it is a 73.0 GB file.
The Q8_0 file is 128.8 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.
If memory is tight, the smallest file is Q2_K at 49.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Laguna S 2.1 Uncensored Heretic
How much VRAM does Laguna S 2.1 Uncensored Heretic need?
About 75.1 GB at Q4_K_M with an 8K context window. That is the 73.0 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 Uncensored Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 51.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Laguna S 2.1 Uncensored Heretic GGUF?
It depends on the quant: Q2_K is 49.2 GB, Q3_K_S is 56.9 GB, Q3_K_M is 62.3 GB, Q3_K_L is 66.8 GB, Q4_K_S is 72.7 GB, Q4_K_M is 73.0 GB and 5 more.
What context length does Laguna S 2.1 Uncensored 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 Uncensored Heretic GGUF?
The files are on Hugging Face in the llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-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 Uncensored 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 on 8 GB VRAM?
Use the Q4_K_S quantization; it requires about 74.8 GB of VRAM at 8 k context, which exceeds 8 GB, so it is not feasible.
Is vision support stable?
Vision is experimental and requires a separate projector file. Compatibility depends on the backend; F16 may be needed for older Vulkan builds.
What license applies?
The model is released under the openmdw-1.1 license, allowing free use and modification.