LLM EXPLORER 65,695 MODELS INDEXED

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ4e by UraionLabs

By UraionLabs · 145 downloads
HF Repo ↗ Copy URL

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ4e is an open-source language model by UraionLabs. Features: 8.8b LLM, VRAM: 5.6GB, License: other.

  4-bit   Apple-silicon   Ar Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv...   Bg   Conversational   Cs   Da Dataset:nvidia/nemotron-post-t... Dataset:nvidia/nemotron-pre-tr...   De   E4b   Edge-ai   El   En   Es   Et   Fi   Fr   Function-calling   Gemma-4   Gemma4   Hi   Hr   Hu   Id   Imatrix   It   Ja   Ko   Lt   Lv   Mac   Metal   Mixed-precision   Mlx   Mlx-lm   Mlx-vlm   Nemotron   Nemotron-3.5   Nemotron-bolt   Nl   No   Nvidia   Omlx   On-device   Oq   Oq4e   Oqe   Pl   Pt   Quantized   Reasoning   Region:us   Ro   Ru   Safetensors   Sharded   Sk   Sl   Sv   Tensorflow   Th   Tool-calling   Tr   Uk   Uraionlabs   Vi   Voice-assistant   Zh
Model Card on HF 🤗: https://huggingface.co/UraionLabs/NVIDIA-Nemotron-3.5-Bolt-E4B-MLX-oQ4e 

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ4e Parameters and Internals

LLM NameNVIDIA Nemotron 3.5 Bolt E4B MLX OQ4e
Repository 🤗https://huggingface.co/UraionLabs/NVIDIA-Nemotron-3.5-Bolt-E4B-MLX-oQ4e 
Base Model(s)  nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16   nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
Model Size8.8b
Required VRAM5.6 GB
Updated2026-10-27
MaintainerUraionLabs
Model Typegemma4
Model Files  5.0 GB: 1-of-2   0.6 GB: 2-of-2
Supported Languagesen es fr de it ja ar bg cs da el et fi hi hr hu id ko lt lv nl no pl pt ro ru sk sl sv th tr uk vi zh
Model ArchitectureGemma4ForConditionalGeneration
Licenseother
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>