Gemma4 26B-A4B

Q4_K_M running on AMD Radeon RX 6900 XT + AMD Radeon Vega with macOS 15.7.5 Sequoia

PERFORMANCE / TOKENS PER SECONDRDNA 2 + GCN / Vega

Prompt processing883.21tok/s

#59 in index

Token generation30.44tok/s

#122 in index

Run fingerprint

Enough context to make the number useful.

ModelGemma4 26B-A4BMoE architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon RX 6900 XT + AMD Radeon Vega31.97 GB VRAM

GPU architectureRDNA 2 + GCN / VegaMetal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.85.4App version used to capture and sign this run

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.