Laguna S 2.1 IQ4 XS Q4 K M needs about 77.3 GB of memory at Q4_K_M (a 75.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 62.7 GB (IQ4_XS) to 75.2 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Laguna S 2.1 IQ4 XS Q4 K M is a 83.6B-parameter Laguna model in GGUF format, quantized by Abiray. Its trained context length is 256K tokens. The repository has 2 quant files, from 62.7 GB (IQ4_XS) to 75.2 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 62.7 GB | 64.8 GB | Too big | Get file → | |
| Q4_K_M | 75.2 GB | 77.3 GB | Too big | Get file → |
What GPU do you need for Laguna S 2.1 IQ4 XS Q4 K M?
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 IQ4 XS Q4 K M quant should you choose?
Q4_K_M is the usual starting point for Laguna S 2.1 IQ4 XS Q4 K M: it balances file size and quality well. Here it is a 75.2 GB file.
If memory is tight, the smallest file is IQ4_XS at 62.7 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
Source
Frequently asked questions about Laguna S 2.1 IQ4 XS Q4 K M
How much VRAM does Laguna S 2.1 IQ4 XS Q4 K M need?
About 77.3 GB at Q4_K_M with an 8K context window. That is the 75.2 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 IQ4 XS Q4 K M on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 64.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Laguna S 2.1 IQ4 XS Q4 K M GGUF?
It depends on the quant: IQ4_XS is 62.7 GB, Q4_K_M is 75.2 GB.
What context length does Laguna S 2.1 IQ4 XS Q4 K M support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 IQ4 XS Q4 K M GGUF?
The files are on Hugging Face in the Abiray/Laguna-S-2.1-IQ4_XS-Q4_K_M-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 IQ4 XS Q4 K M 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.