---
title: "Poolside's Laguna-XS-2.1 Hits 1.4M Downloads With Half-Size APEX Compression"
subtitle: "A community-quantized build of Poolside's 33B coding MoE hits 1.4M downloads, using a MoE-aware compression scheme that beats Q8 at half the size."
url: "https://alphasignal.ai/news/poolside-s-laguna-xs-2-1-hits-1-4m-downloads-with-half-size-apex-compression"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-07-24T15:29:53.000Z"
updated: "2026-08-27T22:48:40.701Z"
type: "Model"
topics:
  - "Llms"
  - "Gpus"
subtopics:
  - "Mixture Of Experts"
  - "Small Models"
  - "Quantization"
upvotes: 3572
source_url: "https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF"
comments: 0
truncated: true
---

# Poolside's Laguna-XS-2.1 Hits 1.4M Downloads With Half-Size APEX Compression

> A community-quantized build of Poolside's 33B coding MoE hits 1.4M downloads, using a MoE-aware compression scheme that beats Q8 at half the size.

A GGUF quantization of Poolside's Laguna-XS-2.1 coding model has quietly become one of the most-downloaded packages on Hugging Face, racking up more than 1.4 million pulls. What's drawing attention is the compression technique used to shrink it: APEX, a Mixture-of-Experts aware method that claims to match Q8\_0 quality at roughly half the size.

The [Laguna-XS-2.1-APEX-GGUF](https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF) repo, maintained by LocalAI's Ettore Di Giacinto, packages seven quant tiers of the base model so you can pick a tradeoff that fits your hardware, from a highest-quality build down to a Mini variant tuned for consumer 16 GB GPUs.

## The model underneath

[Laguna XS 2.1](https://poolside.ai/blog/introducing-laguna-xs-2-1) is Poolside's small open-weight coder: a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token, designed for agentic coding and long-horizon work on a local machine. It shares the same architecture as XS.2, with a notable jump on SWE-bench Multilingual and stronger performance on terminal-style tasks. It fits on a Mac with 36 GB of RAM and ships under OpenMDW-1.1, which is permissive for commercial use.

The architecture is unusual enough to matter for anyone wiring it into an inference stack:

* 40 layers total: 1 leading dense FFN, then 39 MoE layers
* 256 routed experts plus 1 shared expert per MoE layer, with 8 experts active per token and sigmoid gating
* 48 attention heads / 8 KV heads, with a per-layer output gate and hybrid full plus sliding-window attention
* YaRN rope scaling with a 256K context window
* Native interleaved reasoning between tool calls

On benchmarks, XS 2.1's biggest gain over XS.2 shows up on SWE-bench Multilingual, up 5.4 points to 63.1%. For a 3B-active model, that puts it in genuinely useful territory for real code work rather than toy demos.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [mudler/Laguna-XS-2.1-APEX-GGUF on Hugging Face](https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF)
- [Introducing Laguna XS 2.1 - Poolside](https://poolside.ai/blog/introducing-laguna-xs-2-1)
- [apex-quant GitHub repository](https://github.com/mudler/apex-quant)
- [APEX Technical Report](https://github.com/mudler/apex-quant/blob/main/paper/APEX_Technical_Report.md)
- [Poolside drops Laguna S 2.1 - VentureBeat](https://venturebeat.com/infrastructure/poolside-drops-laguna-s-2-1-an-open-weight-coding-model-that-beats-rivals-10x-its-size)