Qwen3 Coder 30B-A3B

Q4_K_M running on AMD Radeon Pro Vega II with macOS 26.6.2 Tahoe

PERFORMANCE / TOKENS PER SECONDGCN / Vega

Prompt processing617.65tok/s

#78 in index

Token generation54.89tok/s

#62 in index

Run fingerprint

Enough context to make the number useful.

ModelQwen3 Coder 30B-A3BMoE architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon Pro Vega II31.98 GB VRAM

GPU architectureGCN / VegaMetal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.85.10App 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.