Rohan Paul (@rohanpaul_ai) “NVIDIA released Nemotron 3.5 Lightning for long-running agent execution. - 30B t” — TopicDigg
Rohan Paul
@rohanpaul_ai
加入 June 2014
0 正在关注 0 粉丝
NVIDIA released Nemotron 3.5 Lightning for long-running agent execution.
- 30B total / 3B active parameters, with up to 1M tokens of context.
Ready for commercial use.
- Local deployment: NVIDIA ships BF16 and much smaller NVFP4 checkpoints, lists 1× DGX Spark or 1× H100 for single-GPU deployment, and also lists RTX 5090 among supported hardware.
- NVIDIA then adds multi-token prediction, DSpark and DFlash speculative decoding, plus NVFP4 quantization to push generation speed further.
- NVIDIA claims up to 4× output speed; on PinchBench, 86% accuracy and 30% faster completion than Qwen3.6 35B at similar accuracy.
显示更多
