Configs › Gemma-4-26B-A4B on Strix Halo, DGX Spark and Mac: measured tok/s

Gemma-4-26B-A4B on Strix Halo, DGX Spark and Mac: measured tok/s

Every tracked benchmark config for Gemma-4-26B-A4B on local hardware: quant, backend, context, tokens per second, source-linked and trust-tiered.

Snapshot 2026-09-16 · 158 configs · 75 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

Measured configs for Gemma-4-26B-A4B

Model	Quant	Backend	Decode	Context	Trust	Source
Gemma-4-26B-A4B	UD-Q4_K_XL	llama.cpp	78 tok/s		Owner-submitted	source

More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.