Qwen3.8 27B

UD-IQ3_XXS running on AMD Radeon RX 6800 XT with macOS 15.7.9 Sequoia

PERFORMANCE / TOKENS PER SECONDRDNA 2

Prompt processing338.01tok/s

#188 in index

Token generation26.43tok/s

#221 in index

Run fingerprint

Enough context to make the number useful.

ModelQwen3.8 27BDense architecture

QuantizationUD-IQ3_XXSExact submitted variant

GPUAMD Radeon RX 6800 XT15.98 GB VRAM

GPU architectureRDNA 2Metal backend

Test context512prompt tokens

Model familyDenseSigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.86.6App 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.