Unverified50% confidenceEventExact time
According to PR 3801 in the NeMo AutoModel repository, the model's multimodal support was unified and consolidated, incorporating 512 routable experts, a RADIO vision tower, and a projection layer with normalization.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedThe official illustration for Nemotron 3.5 Super VL shows the model simultaneously connected to four types of tasks—code, charts, credit memo data extraction, and video analysis—with the design goal of serving as the reasoning hub of multimodal agents.67% similarUnverifiedThe solution was validated on the GLM 5.3 model, a single 8×H200 node, and a full 1-million-token context configuration63% similarUnverifiedThe 200-plus operators included in this kernel collection are sufficient to support the complete inference pipeline for mainstream Transformer architectures as well as various vision and audio models62% similarUnverifiedThe Model Connect repository currently has nearly 60 models configured with multi-device setups, scalable to 2, 4, or 8 GPUs.61% similarUnverifiedThe Nemotron series of open-weight models launched by NVIDIA adopts a MoE (Mixture of Experts) architecture.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047818API
curl https://kongchang.com/api/v1/knowledge/claims/1047818MCP
get_claim(id=1047818)