poolside.Laguna S 2.1 needs about 58.3 GB of memory at F16 (a 56.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 34.4 GB (IQ2_XS) to 125.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
poolside.Laguna S 2.1 is a 118B-parameter Laguna model in GGUF format, quantized by DevQuasar. Its trained context length is 1024K tokens. The repository has 8 quant files, from 34.4 GB (IQ2_XS) to 125.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 34.4 GB | 36.5 GB | Too big | Get file → | |
| IQ2_S | 34.9 GB | 37.0 GB | Too big | Get file → | |
| F16 | 42.9 GB | 45.0 GB | Too big | Get file → | |
| F16 | 56.2 GB (5 parts) | 58.3 GB | Too big | Get file → | |
| F16 | 71.2 GB (6 parts) | 73.3 GB | Too big | Get file → | |
| F16 | 83.5 GB (7 parts) | 85.6 GB | Too big | Get file → | |
| F16 | 96.6 GB (8 parts) | 98.7 GB | Too big | Get file → | |
| F16 | 125.0 GB (10 parts) | 127.1 GB | Too big | Get file → |
What GPU do you need for poolside.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: the best quant that fits is F16 (42.9 GB file, about 45.0 GB in use).
Which poolside.Laguna S 2.1 quant should you choose?
F16 (56.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is IQ2_XS at 34.4 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 poolside.Laguna S 2.1
How much VRAM does poolside.Laguna S 2.1 need?
About 58.3 GB at F16 with an 8K context window. That is the 56.2 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 poolside.Laguna S 2.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 36.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of poolside.Laguna S 2.1 GGUF?
It depends on the quant: IQ2_XS is 34.4 GB, IQ2_S is 34.9 GB, F16 is 42.9 GB, F16 is 56.2 GB, F16 is 71.2 GB, F16 is 83.5 GB and 2 more.
What context length does poolside.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 poolside.Laguna S 2.1 GGUF?
The files are on Hugging Face in the DevQuasar/poolside.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 poolside.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.