Early Astra local tests show 6-10% faster decoding on M4 Max
btibor91 · x · 2026-09-04
After 90 minutes of testing whether Astra improves antirez/ds4 inference, btibor91 reports the strongest result so far is 6-10% faster decoding on an M4 Max, and 3.3% faster decoding on DGX Spark for the best completed comparison. One of the first quantitative data points on running Astra locally, with gains varying by hardware.
More from Models
- Mirai's uzu engine brings speculative decoding to Apple M5, hitting 105 tok/s on Qwen3.6 27B — TheMoonMidas · 2026-09-04
- Premium-tier early access for $300 users sparks debate over staggered model rollouts — GlenBradley · 2026-09-04
- Best local models for 12GB of VRAM: Gemma-4-12B remains the pick — GlennCameronjr · 2026-09-04
- Claude Fable 5.1 Launches, Early Users Say It One-Shots the Best Websites of Any Model — repligate · 2026-09-04
- OUI-1: a fine-tuned Diffusion Gemma for Generative UI, 8x fewer params, open weights — GlennCameronjr · 2026-09-04
- GPT-6 Astra debuts at No.1 on Terminal-Bench, 1.9% ahead of Claude Fable 5.1 — sandersted · 2026-09-04