Unverified50% confidenceReleaseExact time
NVIDIA 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedNemotron Bolt 3.5 74B A9B is a mixture-of-experts (MoE) model with about 74B total parameters, activating only about 9B parameters per token.72% similarUnverifiedNemotron 3.5 Bolt deployment goes through vLLM and supports NVIDIA Ampere (A100), Hopper (H100-80GB), and Blackwell platforms.68% similarUnverifiedNVIDIA's competitive programming expert model Nemotron Labs 3 has 550B total parameters, 55B active parameters, and a 262,144-token context window; it has been listed on Hugging Face with open weights, training data, and recipes.68% similarUnverifiedNVIDIA 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.67% similarUnverifiedNemotron 3.5 Bolt comes with a LiLiCorr drafter for speculative decoding, implemented via DFlash, with 7 speculative tokens by default in the vLLM configuration.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037549API
curl https://kongchang.com/api/v1/knowledge/claims/1037549MCP
get_claim(id=1037549)