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.
More from Infra
- Jensen Huang joins BG2 podcast: does AI revenue justify capex, '27 bottlenecks — elonmusk · 2026-10-16
- Mistral's on-device infra rack revealed: DGX Spark, Mac Studio and more — gregmushen · 2026-10-16
- NVIDIA and Sweden's Wallenberg launch Sferical One, a shared AI supercomputer — nvidia · 2026-10-16
- Next infra frontier: self-evolving systems that adapt and self-verify — _shreya_s · 2026-10-16
- Xiaomi's MiMo RL dashboard reveals $3.47M spent on just 30 training steps — bycloud · 2026-10-16
- Cerebras pushes disaggregated inference: heterogeneous prefill pools feeding wafer-scale decode — ai · 2026-10-16