Marin 535B training starts with full open process and scaling ladder
ysu_nlp · x · 2026-08-22
Marin 535B-A23B started training this week with the entire process open. The model will train on 11x GB200 NVL72 clusters for 3 months on 18.75T tokens (2.7e24 FLOPs). Before the hero run, a scaling ladder from 1.6B to 27.7B parameters was trained to debug issues and forecast performance.
More from Infra
- Muse Spark Open runs locally on a Mac M3 Ultra via llama.cpp: frontier model on desktop — pcuenq · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- vLLM ships Day-0 LoRA RL for Muse Spark Open, lifting AIME from 0.56 to 0.85 — vllm_project · 2026-10-16
- DSpark draft model for Muse Spark Open proposes 7 tokens per pass with 23-42% acceptance — vllm_project · 2026-10-16
- Cloudflare Stream's WebRTC ultra-low-latency live streaming is now Generally Available — ritakozlov · 2026-10-16
- YC-backed Overshoot launches inference optimization, claims $5M saved for AI teams — ycombinator · 2026-10-16