Q4_K_M
The conversion repository lists NVIDIA-Nemotron-3-Nano-30B-A3B-Q4_K_M.gguf at 22.4 GB; its rounded decimal file size is converted to GiB for planning. This does not include context or runtime memory.
- Bits per weight
- 4.5
- Model size
- 20.86 GiB
Model catalog
NVIDIA Nemotron 3 Nano 30B-A3B
NVIDIA's text MoE has 30B total and 3.5B active parameters; weight planning uses total parameters.
Model overview
Available quantizations
Lower-bit quantizations generally use less memory. The compatibility calculator uses these candidates and its transparent approximate memory assumptions; it does not make a performance guarantee.
Compatibility notes
Estimates use the cataloged model-weight size (or a parameter-based estimate), apply weight overhead, and include standard runtime overhead. They do not include context/KV-cache memory. Real requirements vary with runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.
NVIDIA Nemotron 3 Nano 30B-A3B publisher model card; verified value, last verified 2026-10-01. NVIDIA documents 30B total and 3.5B active parameters and the NVIDIA Nemotron Open Model License. Weight planning uses the total count; no context limit is recorded. View source