Nemotron 3.5 Bolt E4B

NVIDIA · Nemotron 3.5
LLMOpenMDW-1.1publicTrusted8B params

NVIDIA's small model of the 3.5 generation, post-trained from Gemma 4 E4B for tool use and low latency; 8B total, 4B effective.

NVIDIA's small model of the 3.5 generation, post-trained from Gemma 4 E4B for tool use and low latency; 8B total, 4B effective.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 8B
  • License: OpenMDW-1.1 (commercial use OK)
  • Hardware: 18 GB+ VRAM
  • dtype: Bf16, Fp16