Feb5E04Da4910Dd56D33F0Cd03747Ff298C1E801 8B-A1B

Q4_K_M running on AMD Radeon Pro 5500M with macOS 26.6.2 Tahoe

PERFORMANCE / TOKENS PER SECONDRDNA 1

Prompt processing787.47tok/s

#72 in index

Token generation76.28tok/s

#41 in index

Run fingerprint

Enough context to make the number useful.

ModelFeb5E04Da4910Dd56D33F0Cd03747Ff298C1E801 8B-A1BMoE architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon Pro 5500M7.98 GB VRAM

GPU architectureRDNA 1Metal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.86.1App 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.