Unverified50% confidenceFactExact time
Nemotron 3.5 Bolt comes with a LiLiCorr drafter for speculative decoding, implemented via DFlash, with 7 speculative tokens by default in the vLLM configuration.
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.70% similarUnverifiedNemotron 3.5 Bolt deployment goes through vLLM and supports NVIDIA Ampere (A100), Hopper (H100-80GB), and Blackwell platforms.70% 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.69% 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.67% similarUnverifiedNemotron 3.5 Bolt uses native 2-bit quantization (IQ2, with quantization-aware training QAT) to compress the model into 24GB of VRAM, allowing it to run on a single consumer-grade or single-card workstation.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037554API
curl https://kongchang.com/api/v1/knowledge/claims/1037554MCP
get_claim(id=1037554)