community pool / model answer

Laguna-XS-2.1

chat · poolside/Laguna-XS-2.1

106.4 tok/s · model median · 6 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
Arc Pro B60 24GB	4-bit	72.5 tok/s	reported	627	- GB	2,048	llama.cpp
Arc Pro B70 32GB	4-bit	87.8 tok/s	reported	491	- GB	2,048	llama.cpp
Radeon AI Pro R9700 32GB ×3	8-bit	100.3 tok/s	reported	306	47.1 GB	792	llama.cpp
RTX 3090 24GB	4-bit	296 tok/s	reported	-	- GB	2,048	lucebox
RX 7900 XTX 24GB ×2	8-bit	124.7 tok/s	reported	245	- GB	32,768	llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.