Qwen3.6 35B-A3B

UD-Q4_K_S running on AMD Radeon PRO W6800X Duo + AMD Radeon PRO W6800X Duo + AMD Radeon PRO W6800X Duo + AMD Radeon PRO W6800X Duo

PERFORMANCE / TOKENS PER SECONDRDNA 2

Prompt processing952.42tok/s

#7 in index

Token generation54.76tok/s

#14 in index

Run fingerprint

Enough context to make the number useful.

ModelQwen3.6 35B-A3BMoE architecture

QuantizationUD-Q4_K_SExact submitted variant

GPUAMD Radeon PRO W6800X Duo + AMD Radeon PRO W6800X Duo + AMD Radeon PRO W6800X Duo + AMD Radeon PRO W6800X Duo127.94 GB VRAM

GPU architectureRDNA 2Metal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · 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.