Laguna XS 2.1 needs about 22.4 GB of memory at Q4_K_M (a 20.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.2 GB 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
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 agentic coding and long‑horizon tasks on local machines.
Good at
- Long‑horizon reasoning
- Agentic coding
- Mixed SWA and global attention
Limits
- Requires 36 GB RAM for full 33 B model
- No vision support
- OpenMDW‑1.1 license limits only text‑to‑text use
Best for
- Local coding assistants
- Long‑form code generation
- Complex terminal‑style tasks
Who it’s for. Developers and researchers needing a large, local LLM for coding and reasoning tasks. The model runs on Mac with 36 GB RAM and is available via Ollama and llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 2.0 GB | Fits | Get file → | |
| IQ2_XXS | 9.4 GB | 11.2 GB | Too big | Get file → | |
| IQ2_XS | 10.4 GB | 12.2 GB | Too big | Get file → | |
| IQ2_S | 10.6 GB | 12.5 GB | Too big | Get file → | |
| IQ2_M | 11.6 GB | 13.5 GB | Too big | Get file → | |
| Q2_K | 12.2 GB | 14.0 GB | Too big | Get file → | |
| Q2_K_L | 12.4 GB | 14.2 GB | Too big | Get file → | |
| IQ3_XXS | 14.3 GB | 16.1 GB | Too big | Get file → | |
| Q3_K_S | 14.9 GB | 16.7 GB | Too big | Get file → | |
| IQ3_XS | 15.6 GB | 17.4 GB | Too big | Get file → | |
| Q3_K_M | 15.6 GB | 17.4 GB | Too big | Get file → | |
| Q3_K_L | 16.1 GB | 18.0 GB | Too big | Get file → | |
| IQ3_M | 16.3 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_XL | 16.3 GB | 18.2 GB | Too big | Get file → | |
| IQ4_XS | 18.2 GB | 20.1 GB | Too big | Get file → | |
| Q4_0 | 19.2 GB | 21.1 GB | Too big | Get file → | |
| IQ4_NL | 19.2 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_S | 19.8 GB | 21.6 GB | Too big | Get file → | |
| Q4_K_M | 20.5 GB | 22.4 GB | Too big | Get file → | |
| Q4_K_L | 20.7 GB | 22.5 GB | Too big | Get file → | |
| Q4_1 | 21.2 GB | 23.0 GB | Too big | Get file → | |
| Q5_K_S | 23.2 GB | 25.1 GB | Too big | Get file → | |
| Q5_K_M | 24.0 GB | 25.8 GB | Too big | Get file → | |
| Q5_K_L | 24.1 GB | 26.0 GB | Too big | Get file → | |
| Q6_K | 29.0 GB | 30.9 GB | Too big | Get file → | |
| Q6_K_L | 29.1 GB | 31.0 GB | Too big | Get file → | |
| Q8_0 | 35.6 GB | 37.4 GB | Too big | Get file → | |
| BF16 | 66.9 GB (2 parts) | 68.8 GB | Too big | Get file → |
For 8 GB VRAM use IQ2_XXS (9.4 GB file, ~11.2 GB VRAM at 8k context). For 16 GB VRAM use Q3_K_S (14.89 GB file, ~16.7 GB VRAM). For 24 GB VRAM use Q4_K_M (20.55 GB file, ~22.4 GB VRAM). 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: the best quant that fits is the main file (0.2 GB file, about 2.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_XXS (9.4 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K_L (12.4 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (21.2 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_L (29.1 GB file, about 31.0 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 20.5 GB file.
The Q8_0 file is 35.6 GB, about 1.7 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 0.2 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 XS 2.1
How much VRAM does Laguna XS 2.1 need?
About 22.4 GB at Q4_K_M with an 8K context window. That is the 20.5 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?
Yes, with the smaller files: the 0.2 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Laguna XS 2.1 GGUF?
It depends on the quant: file is 0.2 GB, IQ2_XXS is 9.4 GB, IQ2_XS is 10.4 GB, IQ2_S is 10.6 GB, IQ2_M is 11.6 GB, Q2_K is 12.2 GB and 22 more.
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 bartowski/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 8 GB VRAM?
Use the IQ2_XXS quant, which requires about 11.2 GB VRAM at 8k context. It may need additional CPU memory for the KV cache.
Does Laguna XS 2.1 support image input?
No, the model is text‑to‑text only and has no vision capability.