# Mindbeam adds Nemotron 3.5 Super VL support to inference engine

_Published Thursday, October 15, 2026 at 12:19 PM EDT · AI · Latest · Tier 2 — Notable_

![Mindbeam adds Nemotron 3.5 Super VL support to inference engine — Primary](https://s.yimg.com/lo/mysterio/api/d35ee055430b53b8e2b27d93dcd164a339c03f11e992b410fa4400ff62d70fe1/lightyear_networkapi/resizefill_w1200%3Bquality_80%3Bformat_webp/https%3A%2F%2Fmedia.zenfs.com%2Fen%2Fprnewswire.com%2F7ccf4cc6daf9d75e8ee04341ec569752.jpg)

Mindbeam announced support for Nvidia's Nemotron 3.5 Super VL in its Litespark Inference Engine and a version of the model adapted to generate CUDA code, which runs computations on Nvidia GPUs. The company said the engine supports tuning for throughput, latency and hardware utilization.

Mindbeam reported that its adapted model passed 82.1% of KernelBench Level 2 problems, compared with 22.8% before adaptation. Its inference performance claims come from a warm-start benchmark using two Nvidia H200 GPUs.

## Sources

- [Yahoo Finance](https://finance.yahoo.com/technology/ai/articles/announcing-mindbeams-collaboration-nvidia-bringing-150000393.html)

---
Canonical: https://techandbusiness.org/newswire/57tyZKSWfnE7sUlZh_h6Dn
Published: 2026-10-15T16:19:23.817Z
Story chronology: 2026-10-15T15:00:00.000Z
Retrieved: 2026-10-15T18:59:52.485Z
Publisher: Tech & Business (techandbusiness.org)