APEX (Adaptive Precision for EXpert Models) quantizations of poolside/Laguna-XS-2.1 — poolside's Laguna XS.2 Mixture-of-Experts model for coding and agentic software engineering.
Model Card
APEX (Adaptive Precision for EXpert Models) quantizations of poolside/Laguna-XS-2.1 — poolside's Laguna XS.2 Mixture-of-Experts model for coding and agentic software engineering. Brought to you by is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention, dense FFN) and applies a layer-wise precision gradient — edge layers get higher precision, middle layers compress more aggressively. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia). In MoE models the routed-expert FFN tensors dominate the weight budget but only ~8/256 experts fire per token, so APEX…
Excerpt from the card by Mudler, licensed openmdw-1.1.
Identity and Version
- Repository
- mudler/Laguna-XS-2.1-APEX-GGUF
- Publisher
- Mudler
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- moe
- Revision
- e9e9293c1979387d1398e41ab824aa73839a8b20
- First published
- 2026-07-24
- Last updated
- 2026-08-17
Files and Weights
9 files, 136.6 GB in total. The weights are 7 files totalling 136.6 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Laguna-XS-2.1-APEX-Balanced.gguf | Weights | 24.3 GB | 997c6b9de70c |
| Laguna-XS-2.1-APEX-Compact.gguf | Weights | 15.8 GB | cb2604e56eec |
| Laguna-XS-2.1-APEX-I-Balanced.gguf | Weights | 24.3 GB | 64f0a1aab7a7 |
| Laguna-XS-2.1-APEX-I-Compact.gguf | Weights | 15.8 GB | b674541db815 |
| Laguna-XS-2.1-APEX-I-Mini.gguf | Weights | 12.8 GB | 04d7ccf014da |
| Laguna-XS-2.1-APEX-I-Quality.gguf | Weights | 21.8 GB | e15e4b9c7c58 |
| Laguna-XS-2.1-APEX-Quality.gguf | Weights | 21.8 GB | fd7dba637bcb |
| README.md | Documentation | 4.5 KB | — |
| .gitattributes | Repository | 2.0 KB | — |
License and Download
- License
- openmdw-1.1
- Access
- Open weights, no gate
- Download size
- 136.6 GB
Released by Mudler through its official repository on Hugging Face.
Built From
- Derived from poolside/Laguna-XS-2.1
- Quantized from poolside/Laguna-XS-2.1
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 136.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Laguna-XS-2.1-APEX-GGUF
What license is Laguna-XS-2.1-APEX-GGUF released under?
openmdw-1.1, as its publisher declares it. Read the license text before commercial use.