Model benchmarks

laguna-xs-2.1 local LLM performance

As of July 2026, laguna-xs-2.1 runs at up to 37.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).

LM Studio

Model size

Unknown

Peak speed

37.2 tok/s

Average speed

27.4 tok/s

Min memory

18.9 GB

Max context

6,887 tokens

Best quality

85.5

Benchmark runs

2

GPUs tested

1

Performance by hardware and tool

Every hardware/tool/quantization combination laguna-xs-2.1 has been benchmarked on, ranked by peak token generation speed. Last updated July 2026.

HardwareToolQuantBest tok/sAvg tok/sMemoryContextQualityRuns
NVIDIA GeForce RTX 4070 Ti SUPERLM Studio37.2 tok/s27.4 tok/s18.9 GB6,887 tokens63.42

Frequently asked questions

How fast is laguna-xs-2.1 for local inference?
Across 2 community benchmark runs, laguna-xs-2.1 reaches up to 37.2 tok/s and averages 27.4 tok/s, with the fastest results on NVIDIA GeForce RTX 4070 Ti SUPER.
How much memory does laguna-xs-2.1 need?
The leanest observed configuration used about 18.9 GB of memory.
Which tools have been used to run laguna-xs-2.1?
Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.