Unverified50% confidenceFactExact time
Among these four models, only Nvidia's Nemotron 3.5 Bolt can run within 24GB of VRAM.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedNemotron 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.74% similarUnverifiedNemotron 3.5 Bolt 74B-A9B uses native 2-bit quantization; the model was designed for low-bit precision from the training stage rather than compressed after the fact.72% similarUnverifiedThe same source claims that NVIDIA Nemotron 3.5 Bolt E4B will be released on October 23, with a memory footprint of about 4GB.68% similarUnverifiedNVIDIA is reportedly training Nemotron 4, while its Nemotron 3.5 has already seen widespread usage.68% similarUnverifiedNVIDIA claims that Nemotron Bolt 3.5 is faster than most popular dense models while being smarter than mainstream MoE models with the same memory footprint.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064204API
curl https://kongchang.com/api/v1/knowledge/claims/1064204MCP
get_claim(id=1064204)