Unverified50% confidenceFactExact time
The DGX Spark (GB10) has 128 GB of unified memory and can run Nemotron 3.5 Super VL using the official NVFP4 + vLLM + LiLiCorr drafter.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
VerifiedThe CPU and GPU of DGX Spark share up to 128 GB of LPDDR5X memory, achieving memory-coherent access via NVLink-C2C high-speed interconnect.74% 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.73% 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.72% similarUnverifiedNemotron 3.5 Super VL can be deployed to run on a single DGX system.70% similarUnverifiedNVFP4 weights can run on a single DGX Spark.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049455API
curl https://kongchang.com/api/v1/knowledge/claims/1049455MCP
get_claim(id=1049455)