Hugging Face's logo

majentik
/
Nemotron-3-Nano-4B-TurboQuant-MLX-4bit

Text Generation
MLX
Safetensors
English
nemotron_h
turboquant
kv-cache-quantization
nemotron
nvidia
mamba2
hybrid
quantized
4bit
conversational
custom_code
4-bit precision
Model card Files
xet
 Community
Nemotron-3-Nano-4B-TurboQuant-MLX-4bit
2.25 GB
  • 1 contributor
 History: 4 commits
majentik's picture
majentik
chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference)
b9738fe verified