Laguna XS 2.1 APEX needs about 23.2 GB of memory at Q4_K_XL (a 21.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 12.9 GB to 28.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Laguna XS 2.1 APEX – 33B Mixture‑of‑Experts model for agentic coding and long‑horizon tasks
Laguna XS 2.1 APEX is a 33B total‑parameter Mixture‑of‑Experts model with 3B activated parameters per token. It supports a 262,144‑token context window and interleaved reasoning with tool calls. The model is available in multiple quantized variants for local deployment.
Good at
- Agentic coding
- Long‑horizon reasoning
- Tool‑enabled interactions
Limits
- Requires 262,144‑token context
- No vision support
- OpenMDW‑1.1 license
Best for
- Local coding assistants
- Complex problem solving
- Tool‑integrated workflows
Who it’s for. Developers and researchers who need a large, local LLM capable of long‑context reasoning and tool use. The model runs on systems with sufficient RAM and supports llama.cpp and Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.9 GB | 14.7 GB | Too big | Get file → | |
| — | 15.8 GB | 17.7 GB | Too big | Get file → | |
| IQ4_XS | 16.9 GB | 18.8 GB | Too big | Get file → | |
| Q4_K_XL | 21.3 GB | 23.2 GB | Too big | Get file → | |
| — | 21.9 GB | 23.7 GB | Too big | Get file → | |
| Q5_K_S | 23.9 GB | 25.7 GB | Too big | Get file → | |
| — | 24.4 GB | 26.2 GB | Too big | Get file → | |
| Q6_K | 28.1 GB | 30.0 GB | Too big | Get file → |
For 24 GB VRAM, use UDX-Q4_K_XL (21.34 GB file, 23.2 GB memory at 8 k context). For better quality per GB, choose UDX-IQ4_XS (16.95 GB file, 18.8 GB memory). For the smallest usable size, pick APEX-I-Mini-v2D-lite (15.84 GB file, 17.7 GB memory).
What GPU do you need for Laguna XS 2.1 APEX?
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: the best quant that fits is the main file (12.9 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (21.9 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.1 GB file, about 30.0 GB in use).
Which Laguna XS 2.1 APEX quant should you choose?
Q4_K_XL (21.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 12.9 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 APEX
How much VRAM does Laguna XS 2.1 APEX need?
About 23.2 GB at Q4_K_XL with an 8K context window. That is the 21.3 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 APEX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Laguna XS 2.1 APEX GGUF?
It depends on the quant: file is 12.9 GB, file is 15.8 GB, IQ4_XS is 16.9 GB, Q4_K_XL is 21.3 GB, file is 21.9 GB, Q5_K_S is 23.9 GB and 2 more.
What context length does Laguna XS 2.1 APEX 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 APEX GGUF?
The files are on Hugging Face in the gbuzhf/Laguna-XS-2.1-APEX-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 APEX 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 APEX on a machine with 36 GB RAM?
Yes, the 33B total parameters and 3B activated per token fit within 36 GB of RAM on a local machine.
Does the model support vision tasks?
No, the model is text‑to‑text only and has no vision support.