---
title: "Ran Laguna S 2.1 *theoretical* (not measured) upper bound calculations for the DGX spark"
date: 2026-07-22
canonical: https://solmaz.io/x/2080000170759233931/
x_url: https://x.com/onusoz/status/2080000170759233931
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
---

Ran Laguna S 2.1 *theoretical* (not measured) upper bound calculations for the DGX spark

poolside/Laguna-S-2.1-NVFP4 - max ~25 tok/s single session. if you are willing to go down to 12 tok/s, you can have 4 sessions in parallel

vcruz305/Laguna-S-2.1-GGUF (IQ1_S) - max ~74 tok/s single session. theoretical 5x20 tok/s = 100 tok/s aggregate upper bound

Calculated assuming no speculative decoding, so might increase well over these numbers

See my local frontier app and my previous posts for more info on the methodology

https://osolmaz-local-frontier.hf.space/compare?models=poolside%2FLaguna-S-2.1-NVFP4%2Cpoolside%2FLaguna-S-2.1-GGUF%2Cvcruz305%2FLaguna-S-2.1-GGUF&hardware=nvidia-dgx-spark

*Quotes a post by @sudoingX (https://x.com/sudoingX/status/2079623151953310190); its text is omitted here because it is not covered by this site's license.*