Qwen3 4B

Q4_K_M running on RX 5600 XT

PERFORMANCE / TOKENS PER SECONDRDNA 1

Prompt processing100tok/s

#20 in index

Token generation52.1tok/s

#10 in index

Run fingerprint

Enough context to make the number useful.

ModelQwen3 4BDense architecture

QuantizationQ4_K_MExact submitted variant

GPURX 5600 XT6 GB VRAM

GPU architectureRDNA 1Metal backend

Test context512prompt tokens

Model familyDenseStandard configuration

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.