Nemotron 3.5 Lightning (30B-A3B, Q4)
NVIDIA's Nemotron 3.5 Lightning at 30B parameters — text-only, with native reasoning, native tool calling, and a 256K context window. Capable-tier on-device option: about 25GB of memory on most machines, about 18GB on Apple Silicon.
| At a glance | |
|---|---|
| Made by | NVIDIA |
| Download size | 25.4 GB |
| Parameters | 30B |
| Quantization | Q4_K_M |
| Context window | 262K tokens |
| Uses tools | Yes |
| Best for | Reasoning |
| Runs on | llama.cpp, MLX |
| License | OpenMDW 1.1 |
| Added to the catalog | 2026-08-15 |
Gezel downloads this model the first time a gezel needs it, checks the file against its published hash, and applies tuned settings for it.