Skip to content
localmodel.run

Text model · Laguna

LA Laguna XS 2.1: RAM and VRAM requirements

Laguna XS 2.1 needs about 22.2 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~20 GB to download; KV cache and overhead add the rest), or about 38.2 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 4090 (24GB).

Laguna family · 33.4B params (Mixture-of-Experts: activates only 3B of 33.4B params per token, so generation is faster than the total size suggests) · released Jun 2026.

Shopping for hardware? See what runs Laguna XS 2.1 →

License OpenMDW-1.1 · Commercial OK ↓ 33.7K/mo ♥ 200 on HuggingFace
Q4_K_M GGUF
20 GB
Q8_0 GGUF
36 GB
Memory @ Q4 (4k)
~22.2 GB
Context
256 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

Laguna XS 2.1 runs on 12 of 40 tracked devices at Q4_K_M.

9 run well 3 tight fit 28 too small
Fit check Q4_K_M
No, not enough memory
needs 22.2 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)20 GB
+
KV cache (4k)1.4 GB
+
Overhead0.8 GB
=
Total22.2 GB

How context length changes it

4k context ~22.2 GB 32k context ~31.9 GB 128k context ~65.2 GB

Longer context grows the KV cache, which for Laguna XS 2.1 is sized by its 3B active params, not the full 33.4B. It needs ~22.2 GB at 4k and ~65.2 GB at 128k.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 14 GB est
Q3_K_M 16.3 GB est
Q4_K_M (default) 20 GB
Q5_K_M 23.8 GB est
Q6_K 27.4 GB est
Q8_0 36 GB
FP16 67 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run laguna-xs-2.1

Which devices can run Laguna XS 2.1?

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

NVIDIA GPUs

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down Gemma 4 31B 32.7B Next size up Yi 1.5 34B 34B

Similar models

Head-to-head

FAQ

How much VRAM or RAM does Laguna XS 2.1 need?

At Q4_K_M, Laguna XS 2.1 needs about 22.2 GB (weights ~20 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~38.2 GB.

What is the Q4_K_M GGUF file size of Laguna XS 2.1?

The Q4_K_M GGUF file is about 20 GB to download, and the Q8_0 GGUF is about 36 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~22.2 GB of memory at Q4_K_M.

Can Laguna XS 2.1 run on a laptop?

Laguna XS 2.1 is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Is Laguna XS 2.1 cheaper to run because it is a MoE model?

It is faster, not lighter. Laguna XS 2.1 activates only 3B of 33.4B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 33.4B.

Can I use Laguna XS 2.1 commercially?

Yes. Laguna XS 2.1 is licensed OpenMDW-1.1, which permits commercial use.

Understand the numbers

Short guides to the ideas behind Laguna XS 2.1's memory and quant figures.

poolside's open-weight coding MoE: 33B total, 3B active (256 experts, 8 per token), 256K context, tuned for SWE-bench-style agentic work. Sizes from the Ollama tag listing. The 2.1 release relicensed from Apache-2.0 (XS.2) to OpenMDW-1.1, the Linux Foundation's permissive open-weights license.

Sources

Last validated 2026-08-03. Memory figures are estimates. See methodology.