hugpadhugpad

UraionLabs / NVIDIA-Nemotron-3.5-Bolt-E4B-MLX-oQ5e

Agents8.3B920Updated Oct 23, 2026
Hugging Face

Downloads

92

Likes

0

Last updated

Oct 23, 2026

License

openmdw-1.1

NVIDIA Nemotron 3.5 Bolt E4B quantized for Apple Silicon with MLX: 6.3 GB, mixed precision, 5-bit base with sensitive layers at higher bits, imatrix-calibrated.

Tasks & library

  • text generation
  • mlx

Tags

  • mlx
  • gemma4
  • mlx-vlm
  • mlx-lm
  • apple-silicon
  • mac

Technical specifications

Parameters8.3B
Librarymlx
Languages34 languages
Base modelnvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
Licenseopenmdw-1.1