Laguna S 2.1 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 11 quants, from 0.4 GB to 125.0 GB (Q8_0). 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 with 1M context
Laguna S 2.1 is a 118B total parameter Mixture‑of‑Experts model with 8B activated per token. It features 48 layers, 256 routed experts plus one shared expert, and a 1,048,576‑token context window. The model supports native reasoning and tool calls.
Good at
- Long‑horizon reasoning
- Agentic coding
- Tool‑enabled workflows
Limits
- 1M context only
- No vision support
- Requires 8K context for memory estimates
Best for
- Complex coding assistants
- Research agents
- Long‑form content generation
Who it’s for. Developers and researchers needing a large, text‑only model with extensive context and reasoning capabilities. Suitable for building agentic applications and long‑form content tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 2.5 GB | Fits | Get file → | |
| IQ2_XS | 34.4 GB | 36.5 GB | Too big | Get file → | |
| IQ2_M | 38.4 GB | 40.5 GB | Too big | Get file → | |
| IQ3_XS | 48.0 GB | 50.1 GB | Too big | Get file → | |
| IQ3_M | 51.5 GB | 53.6 GB | Too big | Get file → | |
| IQ4_XS | 62.7 GB | 64.8 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 → | |
| 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 → | |
| Q8_0 | 125.0 GB | 127.1 GB | Too big | Get file → |
For 8‑GB VRAM use Q4_K_M (71.16 GB file, ~73.3 GB memory at 8K context). For 16‑GB VRAM use Q5_K_M (83.48 GB file, ~85.6 GB memory). For maximum fidelity use Q8_0 (125.02 GB file, ~127.1 GB memory).
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: 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 the main file (0.4 GB file, about 2.5 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (38.4 GB file, about 40.5 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 71.2 GB file.
The Q8_0 file is 125.0 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 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
How much VRAM does Laguna S 2.1 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 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 GGUF?
It depends on the quant: file is 0.4 GB, IQ2_XS is 34.4 GB, IQ2_M is 38.4 GB, IQ3_XS is 48.0 GB, IQ3_M is 51.5 GB, IQ4_XS is 62.7 GB and 5 more.
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 AtomicChat/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 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.
Can I run Laguna S 2.1 on 8 GB VRAM?
Use the Q4_K_M quant; it requires about 73.3 GB memory at 8K context, so 8 GB VRAM is insufficient. A smaller quant like IQ2_XS would fit but with lower quality.
Does Laguna S 2.1 support vision?
No, the model is text‑to‑text only.