← Back to Models

nvidia-nemotron-3-nano-30b-a3b-mlx

nvidia-nemotron-3-nano-30b-a3b-mlx

Publisher
lmstudio-community
Architecture
nemotron_h(sparse)
Parameters
30B
Quantization
4bit (4.0 bpw)
Format
mlx
Max Context
262k tokens
Type
llm
File Size
16.57 GB
Est. RAM
18.1 GB
Est. VRAM
18.1 GB(~3B active)
Capabilities
trained_for_tool_use

Benchmark Results

Compare Models