Nemotron 3.5 Bolt 74B-A9B (GGUF Q8_0)

NVIDIA (GGUF: unsloth) · Nemotron 3.5
LLMOpenMDW-1.1publicTrusted75B params

llama.cpp GGUF build (Q8_0, Unsloth) of Nemotron 3.5 Bolt: hybrid Mamba-2 and Transformer MoE, 74B total, 9B active, 256K context.

llama.cpp GGUF build (Q8_0, Unsloth) of Nemotron 3.5 Bolt: hybrid Mamba-2 and Transformer MoE, 74B total, 9B active, 256K context.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 75B
  • License: OpenMDW-1.1 (commercial use OK)
  • Hardware: 87 GB+ VRAM
  • dtype: Int8