gemma-embedding2 0.3B

12 records across 1 hardware.

hardware	model	quant	backend	tok/s	pp tok/s	W	ttft s	ctx/tg	date	class	flags	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	652.25	–	–	8	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	1460.06	–	–	8	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	1782.69	–	–	32	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	2845.38	–	–	32	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	2264.76	–	–	128	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	2552.93	–	–	128	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	2576.44	–	–	256	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	2777.91	–	–	256	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	2893.72	–	–	512	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	3177.44	–	–	512	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	2366.24	–	–	1024	2026-10-14	sourced	–	source
Intel(R) Xeon(R) Platinum 8488C	gemma-embedding2 0.3B	Q4_K_M	llama.cpp	–	2535.64	–	–	1024	2026-10-14	sourced	–	source