Verified80% confidenceFactExact time
NVIDIA claims that the weights of Nemotron 3.5 Bolt 74B-A9B can run in 24GB of memory, and that 24GB refers only to the weights themselves, excluding context, KV cache and runtime overhead.
4
Sources
80%
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 uses 2-bit quantization combined with quantization-aware training (QAT) to compress the entire model to about 24GB of VRAM usage.74% similarUnverifiedAn NVIDIA H100 single card has 80 GB of VRAM, and an 8-card node with 640 GB is still insufficient to load the full weights of Qwen3.8.73% similarVerifiedNVIDIA's upcoming RTX Spark laptop offers up to 128 GB of unified memory in its highest configuration.73% similarUnverifiedThe M3 Max is equipped with up to 128 GB of unified memory, capable of running unquantized 70B and even larger models, far exceeding the maximum 24 GB limit of consumer-grade NVIDIA graphics cards.72% similarUnverifiedThe NVIDIA A100 has a memory bandwidth of 2 TB/s; loading a 280 GB FP32 model takes approximately 140 ms, meaning weight loading alone limits generation to a maximum of approximately 7 tokens per second.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036611API
curl https://kongchang.com/api/v1/knowledge/claims/1036611MCP
get_claim(id=1036611)