Why is NVIDIA MIG still limited to 7 instances on B300/Rubin?
StasBekman · x · 2026-09-01
A developer questions why the MIG (Multi-Instance GPU) limit of 7 instances, established in the A100 era, persists on the newer B300/288GB and upcoming Rubin architectures. The user seeks to raise the limit to at least 8 for better utilization and asks where to file feature requests.
Related event: Developers Question NVIDIA's Stale 7-Instance MIG Limit(2 posts)→
More from Infra
- RL train-sample systems are frontier AI's hardest infra problem — and a trade secret — brianryhuang · 2026-10-16
- Local tuning of GLM-5.3-Flash on 2×GB10 lifts decode from 49 to 58 tok/s — EAccelerate_42 · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16
- Optuna creator Akiba: when 2 hyperparameters cost $20M, what's left for BO/HPO — Stefania_druga · 2026-10-16
- Amazon Proposes Per-Request Validated Evidence Caching for Production RAG — _reachsumit · 2026-10-16
- LinkedIn's TransX report: sequence transduction for recsys, +6.02% CTR in A/B tests — _reachsumit · 2026-10-16