Ornith 1.5 35B

Q4_K_M running on AMD Radeon Pro 5500M with macOS 15.7.9 Sequoia

PERFORMANCE / TOKENS PER SECONDRDNA 1

Prompt processing132.87tok/s

#248 in index

Token generation12.47tok/s

#247 in index

Run fingerprint

Enough context to make the number useful.

ModelOrnith 1.5 35BMoE architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon Pro 5500M7.98 GB VRAM

GPU architectureRDNA 1Metal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · ncmoe 32 · amd-gpu · Metal

ToshLLM versionv0.87.0App 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.