Qwen3.8 27B

UD-IQ3_S running on AMD Radeon Pro W5700X with macOS 15.8.1 Sequoia

PERFORMANCE / TOKENS PER SECONDRDNA 1

Prompt processing148.95tok/s

#274 in index

Token generation16.16tok/s

#269 in index

Run fingerprint

Enough context to make the number useful.

ModelQwen3.8 27BDense architecture

QuantizationUD-IQ3_SExact submitted variant

GPUAMD Radeon Pro W5700X15.98 GB VRAM

GPU architectureRDNA 1Metal backend

Test context512prompt tokens

Model familyDenseSigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.87.12App 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.