Ornith 1.5 35B Hits 81.8 on GPQA with Thinking Mode, Decodes at 303 tok/s

MikePFrank · x · 2026-08-23

Enabling 'thinking mode' boosts Ornith 1.5 35B's GPQA-diamond score from 52.0 to 81.8, leveling it with top dense 27B models. The model decodes at 303 tok/s on a single RTX 5090 (Q4KM, 20GB VRAM), maintaining 258 tok/s at 32k context. Standard benchmarks include MMLU 82.2 and GSM8K 91.7. NVFP4 builds on vLLM show similar performance.

Original post →

More from Infra

Infra channel →