What hardware do you need to run Laguna XS 2.1?

Laguna XS 2.1 at Q4_K_M is 20 GB of weights, with a context ceiling of 256k tokens. poolside's agentic-coding MoE: 33B total but only 3B active per token. On the cheapest machine that runs it, a Framework Desktop, 32GB, it generates 44 tok/s at 32k of context, worked out from memory bandwidth.

How good is Laguna XS 2.1, really?

It has not been placed on the intelligence index yet. See the whole table.

Head to head with the models that need much the same memory at 32k of context: vs Qwen3 30B-A3B Instruct 2507, vs Qwen3-Coder 30B-A3B, vs Hy-Memory 30B-A3B.

What Laguna XS 2.1 costs either way

Renting the same model costs $0.06 per million input tokens and $0.12 per million output (OpenRouter, cheapest active endpoint, checked 2026-10-29). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill. What a million tokens costs each way puts the two prices side by side.

Machines that run Laguna XS 2.1

Every machine here runs it, but not to the same length. The Strix Halo Framework Desktop, 32GB stops at 64k; the Mac mini M5 Pro, 48GB takes it to 256k, which is this model's own ceiling and the longest the calculator offers. The weights are the same size on every machine; what differs is the memory left for the key-value cache, which grows with every token you keep.

The table is the cheapest machine in each family, not the only one that runs it: 41 of the 56 machines on this site hold it at 32k. Within a family only memory decides, so that is every Mac Studio and Strix Halo box at any size, every NVIDIA card with 24GB or more, every Mac mini and MacBook Pro with 48GB or more, the Radeon AI PRO R9700, 32GB and the DGX Spark, 128GB. One table sets every machine against the others: price, the memory its GPU can use, what it holds and how long it takes to pay for itself.

One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration. The longest context is the longest setting the calculator offers that the machine still holds this model at, cache included, and no machine is shown taking it past its own 256k limit. Each one opens the calculator on that machine at that length.

For scale, the calculator starts from 80 tok/s for a hosted API and times a local machine against it. 2 of the 7 above reach it, and the slowest is 29 tok/s.

The cheapest machine that runs it is sold with 32 GB. There is a page on what 32 GB runs, machine by machine: it names the 6 machines here sold at that size, and the 37 current models the roomiest of them holds at 32k, this one among them.

It fits in less memory than that: the smallest size here that runs it at 32k is 24 GB, on the GeForce RTX 3090, 24GB at $1,499, card only, which hands a model 23 GB and is no longer sold.

Run Laguna XS 2.1 at 256k on the Mac mini M5 Pro, 48GB

How much memory does Laguna XS 2.1 need at 256k?

Every figure above is priced at 32k of context. At 256k, which is this model's own ceiling and the longest the calculator offers, Laguna XS 2.1 needs 31.1 GB rather than 21.7 GB. The weights are the same either way; the key-value cache goes from 1.4 GB to 10.8 GB.

28 of the 37 machines here still sold at a published price hold Laguna XS 2.1 at 32k and 24 hold it at 256k. The cheapest still sold goes from the Framework Desktop, 32GB at $1,269 to the Corsair AI Workstation 300, 64GB at $1,700.

On the Corsair AI Workstation 300, 64GB it runs 44 tok/s estimated at 32k and 11 tok/s estimated at 256k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

Two more machines, at a shorter window

The table above lists the machines that run it at 32k, the context the calculator starts on, where Laguna XS 2.1 needs 22 GB. Two more machines hold it at a shorter window, because the weights are the same size either way and the key-value cache is not. None of them is cheaper than the table above, which starts at $1,269.

One machine per family, cheapest first, from the same list as the table above. Each window is the longest setting the calculator offers that the machine still holds this model at, and it opens the calculator on that machine at that length. What it needs there is the weights plus the key-value cache at that window, measured against the memory each machine's GPU can address, which that machine's own page gives.

The specifics

Parameters

33.4B, of which 3B are active per token

Quantisation

Q4_K_M

Weights on disk

20 GB

KV cache

1.4 GB at 32k context — 3 sliding-window layers (512) per full-attention layer. The runtime keeps the KV cache in FP8, so real usage is about half the figure here. How weights and cache add up.

Maximum context

256k tokens

Licence

OpenMDW 1.1

Sources

poolside/Laguna-XS-2.1, poolside/Laguna-XS-2.1-GGUF