Laguna S 2.1 needs about 98.1 GB of memory at Q4_K_M (a 96.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 2.2 GB (BF16) to 235.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Laguna S 2.1 – 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 parameters per token. It features a 1,048,576‑token context window, mixed global and sliding‑window attention, and interleaved reasoning support. The model is released under OpenMDW‑1.1, allowing free commercial use.
Good at
- Long‑horizon coding
- Agentic tool use
- Large context reasoning
Limits
- No vision support
- Requires 8‑K context for memory estimates
- License is permissive but no pre‑trained weights beyond GGUF
Best for
- Building code‑generation agents
- Running long‑form reasoning tasks
- Serving with llama.cpp on GPUs
Who it’s for. Developers and researchers needing a large‑context, Mixture‑of‑Experts LLM for coding and reasoning. The model is suitable for commercial deployment due to its permissive license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 2.2 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 96.0 GB | 98.1 GB | Too big | Get file → | |
| Q8_0 | 128.8 GB | 130.9 GB | Too big | Get file → | |
| F16 | 235.2 GB | 237.3 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q4_K_M quant (file size 96 GB, estimated 98 GB memory at 8 K context). For 16‑GB VRAM, use Q8_0 (128.75 GB, 130.9 GB memory). The BF16 and F16 variants require more than 200 GB memory and are not recommended for typical GPU setups.
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is BF16 (2.2 GB file, about 4.3 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (2.2 GB file, about 4.3 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (2.2 GB file, about 4.3 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (2.2 GB file, about 4.3 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (2.2 GB file, about 4.3 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (2.2 GB file, about 4.3 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (2.2 GB file, about 4.3 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 96.0 GB file.
The Q8_0 file is 128.8 GB, about 1.3 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 BF16 at 2.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Laguna S 2.1
How much VRAM does Laguna S 2.1 need?
About 98.1 GB at Q4_K_M with an 8K context window. That is the 96.0 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 on an 8 GB GPU?
Yes, with BF16: the 2.2 GB file needs about 4.3 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: BF16 is 2.2 GB, Q4_K_M is 96.0 GB, Q8_0 is 128.8 GB, F16 is 235.2 GB.
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 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.
Can I run Laguna S 2.1 on 8 GB VRAM?
Use the Q4_K_M quant; it requires about 98 GB memory at 8 K context, so 8 GB VRAM is insufficient.
What context length does the GGUF support?
The GGUFs are configured for a 256K context window; the base model supports up to 1M tokens.
Is there a vision capability?
No, Laguna S 2.1 is text‑to‑text only.