Can I run Laguna S 2.1 on a Dual RTX 3090?
Key facts
Only slowly: Laguna S 2.1 is too big for the graphics memory of a Dual RTX 3090, so part of it runs from normal memory.
It needs about 97.3 GB at standard quality (estimate). Checked . poolside Q4_K_M GGUF.
We don't give a speed for this model yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Updated · Laguna S 2.1 on every card
How much memory it needs
That is more than this machine has free, so the rest spills into normal memory.
Get a 1-line alert when a faster quant for Laguna S 2.1 drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new low-bit GGUF/MLX quant fits 128–256 GB rigs or when multi-GPU & Mac Studio prices drop >10% — weekly, zero spam.
What runs Laguna S 2.1 fully in graphics memory
The cheapest machine on our list that holds the whole model in its graphics memory:
Mac Studio M5 Ultra 256GBabout $11,565€12,500
EU shops · Shown to visitors in Europe.US shops · Shown to visitors outside Europe.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
Price details
$11,565€12,500
How we priced this
Not checked against a shop listing (price unverified). Price from 16 Oct 2026.
Our estimate for this configuration; Apple's own store price was not checked. About €12,500–€13,000; we use the low end. 256 GB needs the 36-core CPU / 80-core GPU chip.
Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.
See our picks for Laguna S 2.1 in Find hardware. Add your budget to see cheaper machines.
For comparison, a Dual RTX 3090 with 64 GB of normal memory (RAM) costs about $3,808€3,592. With 128 GB it gives the same answer and costs about $5,528€5,452. Machine details: Dual RTX 3090, 64 GB RAM, Dual RTX 3090, 128 GB RAM.
If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work
As an Amazon Associate I earn from qualifying purchases.
Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.
Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.
Laguna S 2.1 on other graphics cards
Runs slowly2
Part of the model spills into normal memory, which is much slower.
Doesn't fit8
Not enough graphics memory: it needs about 97.3 GB.
- RTX 3060 12GBhas 12 GB
- RTX 4060 Ti 16GBhas 16 GB
- RTX 3090has 24 GB
- RTX 4090has 24 GB
- RTX 5080has 16 GB
- RX 9060 XT 16GBhas 16 GB
- RTX 5090has 32 GB
- RX 7900 XTXhas 24 GB
More about the model itself, what it is good at and its licence: Laguna S 2.1.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this machine.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Runs slowly | 96.0 GBmeasured file | 0.5 GB | 0.8 GB | 97.3 GB | 46.8 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Runs slowly | 113.6 GB | 0.5 GB | 0.8 GB | 114.9 GB | 46.8 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Runs slowly | 126.3 GB | 0.5 GB | 0.8 GB | 127.5 GB | 46.8 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Doesn't fit | 236.0 GB | 0.5 GB | 0.8 GB | 237.3 GB | 46.8 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Runs slowly | 96.0 GBmeasured file | 1.7 GB | 0.8 GB | 98.5 GB | 46.8 GB |
With 64 GB of normal memory (RAM) instead of 128 GB, Q5 and Q8 don't fit.
speed: not estimated for MoE yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . poolside Q4_K_M GGUF.
Poolside's coding mixture of experts: 118B total, about 8B active, 256 routed experts with 10 per token plus one shared expert, context 1,048,576. Open weights under OpenMDW-1.1. 12 of 48 layers attend to the whole context; the other 36 use a 512-token window. The DFlash draft (2.23 GB) is not in these file sizes.
Measured Laguna S 2.1 on a Dual RTX 3090 yourself? Send us your llama-bench result.
Questions
- Can I run Laguna S 2.1 on a Dual RTX 3090?
- Only slowly: Laguna S 2.1 is too big for the graphics memory of a Dual RTX 3090, so part of it runs from normal memory.
- How much memory does Laguna S 2.1 need?
- About 97.3 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 96.0 GB for the model file (measured), 0.5 GB to hold the conversation and 0.8 GB of working space.
- How fast is Laguna S 2.1 on a Dual RTX 3090?
- We don't give a speed for this model yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate