Laguna XS 2.1 APEX needs about 23.7 GB of memory at its main file (a 21.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 12.8 GB to 24.3 GB. 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 coding and agentic tasks
Laguna XS 2.1 APEX is a 33B total parameter Mixture‑of‑Experts model with 3B activated per token. It supports long‑horizon coding and agentic work on local machines. The model is available in multiple APEX quantizations for llama.cpp and Ollama.
Good at
- Agentic coding
- Long‑horizon reasoning
- Tool‑calling
Limits
- Requires 36 GB RAM for full 33B model
- No vision support
- Large context window of 262,144 tokens
Best for
- Local coding assistants
- Software engineering agents
- Long‑form code generation
Who it’s for. Developers and researchers needing a local, high‑capacity coding model with agentic capabilities. The model can be run on machines with 36 GB RAM and a recent llama.cpp build supporting arch=laguna.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.8 GB | 14.7 GB | Too big | Get file → | |
| — | 15.8 GB | 17.6 GB | Too big | Get file → | |
| — | 15.8 GB | 17.6 GB | Too big | Get file → | |
| — | 21.8 GB | 23.7 GB | Too big | Get file → | |
| — | 21.8 GB | 23.7 GB | Too big | Get file → | |
| — | 24.3 GB | 26.2 GB | Too big | Get file → | |
| — | 24.3 GB | 26.2 GB | Too big | Get file → |
For 8 GB VRAM use the 12.83 GB file (14.7 GB estimated memory at 8 k context). For 16 GB VRAM use the 15.78 GB file (17.6 GB estimated). For 24 GB VRAM use the 21.82 GB file (23.7 GB estimated). Estimates are approximate.
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 (12.8 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (21.8 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (24.3 GB file, about 26.2 GB in use).
Which Laguna XS 2.1 APEX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 12.8 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 23.7 GB at its main file with an 8K context window. That is the 21.8 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 12.8 GB, file is 15.8 GB, file is 15.8 GB, file is 21.8 GB, file is 21.8 GB, file is 24.3 GB and 1 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 mudler/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 on 8 GB VRAM?
No. The smallest quantized file is 12.83 GB and requires about 14.7 GB of memory at 8 k context. 8 GB VRAM is insufficient.
Does Laguna XS 2.1 support vision tasks?
No. The model is text‑to‑text only and has no vision modality.
What license does Laguna XS 2.1 use?
It is released under the openmdw-1.1 license, which is fully permissive for commercial and non‑commercial use.