Gemma 4 26B-A4B

UD-Q4_K_M running on AMD Radeon RX 6600 XT

PERFORMANCE / TOKENS PER SECONDRDNA 2

Prompt processing231.85tok/s

#59 in index

Token generation17.29tok/s

#66 in index

Run fingerprint

Enough context to make the number useful.

ModelGemma 4 26B-A4BMoE architecture

QuantizationUD-Q4_K_MExact submitted variant

GPUAMD Radeon RX 6600 XT7.98 GB VRAM

GPU architectureRDNA 2Metal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · ncmoe 22 · amd-gpu · Metal

Prompt processing and generation are reported separately so memory bandwidth and decode behavior stay visible.

Quantization, GPU family, VRAM and context travel with the result instead of being hidden behind one score.

This result remains explicitly labeled as a community submission.