Qwen3.8 27B

UD-IQ2_S running on AMD Radeon Pro Vega 64 with macOS 14.8.7 Sonoma

PERFORMANCE / TOKENS PER SECONDGCN / Vega

Prompt processing104.51tok/s

#319 in index

Token generation13.11tok/s

#292 in index

Run fingerprint

Enough context to make the number useful.

ModelQwen3.8 27BDense architecture

QuantizationUD-IQ2_SExact submitted variant

GPUAMD Radeon Pro Vega 6415.98 GB VRAM

GPU architectureGCN / VegaMetal backend

Test context512prompt tokens

Model familyDenseSigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.87.8App 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.