Nemotron 3.5 Super VL 120B-A12B (GGUF Q8_0 + vision)

NVIDIA (GGUF: ggml-org) · Nemotron 3.5
LLMOpenMDW-1.1publicTrusted124B params

llama.cpp GGUF build (Q8_0, ggml-org) of Nemotron 3.5 Super VL, 120B MoE with 12B active. The BF16 projector reads images.

llama.cpp GGUF build (Q8_0, ggml-org) of Nemotron 3.5 Super VL, 120B MoE with 12B active. The BF16 projector reads images.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 124B
  • License: OpenMDW-1.1 (commercial use OK)
  • Hardware: 144 GB+ VRAM
  • dtype: Int8