Laguna-XS-2.1 needs about 21.4 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 19.6 GB (Q4_K_M) to 66.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Laguna‑XS‑2.1: 33B Mixture‑of‑Experts model for long‑horizon coding and agentic tasks
Laguna‑XS‑2.1 is a 33 B total‑parameter Mixture‑of‑Experts model with 3 B activated parameters per token. It supports a 262 144‑token context window and is optimized for local deployment on machines with 36 GB RAM. The model is available in several quantizations via GGUF.
Good at
- Long‑horizon coding
- Agentic reasoning
- Terminal‑style tasks
Limits
- Requires 36 GB RAM for full precision
- No vision or audio modalities
- OpenMDW‑1.1 license only
Best for
- Local coding assistants
- Long‑form code generation
- Agentic workflow automation
Who it’s for. Developers and researchers who need a powerful, text‑only model that can run locally on a high‑memory machine. The model is fully permissive under OpenMDW‑1.1, allowing commercial use without permission.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 19.6 GB | 21.4 GB | Too big | Get file → | |
| Q8_0 | 35.6 GB | 37.4 GB | Too big | Get file → | |
| BF16 | 66.9 GB | 68.8 GB | Too big | Get file → |
For 8 k context, Q4_K_M uses ~21.4 GB of VRAM and is suitable for 8 GB GPUs. Q8_0 requires ~37.4 GB and BF16 needs ~68.8 GB. Choose the quant that fits your VRAM budget; estimates are approximate.
What GPU do you need for Laguna-XS-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: the best quant that fits is Q4_K_M (19.6 GB file, about 21.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (19.6 GB file, about 21.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.6 GB file, about 37.4 GB in use).
Which Laguna-XS-2.1 quant should you choose?
Q4_K_M is the usual starting point for Laguna-XS-2.1: it balances file size and quality well. Here it is a 19.6 GB file.
The Q8_0 file is 35.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Laguna-XS-2.1
How much VRAM does Laguna-XS-2.1 need?
About 21.4 GB at Q4_K_M with an 8K context window. That is the 19.6 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-XS-2.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Laguna-XS-2.1 GGUF?
It depends on the quant: Q4_K_M is 19.6 GB, Q8_0 is 35.6 GB, BF16 is 66.9 GB.
What context length does Laguna-XS-2.1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Laguna-XS-2.1 GGUF?
The files are on Hugging Face in the ggml-org/Laguna-XS-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-XS-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‑XS‑2.1 on a 8 GB GPU?
With Q4_K_M quantization, the model needs about 21.4 GB of VRAM at 8 k context, so a 8 GB GPU is insufficient.
Does Laguna‑XS‑2.1 support image inputs?
No, the model is text‑to‑text only and does not include vision capabilities.
Is the model licensed for commercial use?
Yes, it is released under the fully permissive OpenMDW‑1.1 license, allowing commercial deployment.