Unverified50% confidenceOpinionExact time
In the name Nemotron-3.5-Super-VL-120B-A12B, '120B-A12B' most likely indicates a MoE architecture with 120B total parameters and 12B activated parameters, and 'VL' points to vision-language multimodal capability.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedNVIDIA released the Nemotron-3.5-Super-VL-120B-A12B model family, covering a base version as well as multiple quantization formats including NVFP4 and BF16, and introduced the LiLiCorr speculative decoding scheme.68% similarUnverifiedTypical representatives of the MoE architecture include Mixtral 8x7B and DeepSeek-V2.61% similarUnverifiedQwen2.5-VL-7B is a vision-language model released by Alibaba's Tongyi Qianwen team, with a parameter scale of about 7 billion; the 7B size can run locally on consumer-grade hardware.61% similarUnverifiedNVIDIA released Nemotron 3.5 Bolt 74B-A9B 24GB, a vision-language model (VLM) with 74B total parameters and 9B activated parameters, published on Hugging Face.60% similarUnverifiedIn a developer blog post, NVIDIA introduced a vision-language model called Nemotron 3.5 Super VL, aimed at multimodal agent scenarios.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037568API
curl https://kongchang.com/api/v1/knowledge/claims/1037568MCP
get_claim(id=1037568)