What are the hardware requirements for NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e?

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e requires approximately 8.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e and how large is it?

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e is developed by UraionLabs, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e?

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e by UraionLabs — VRAM 8.9GB

Name: NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e
Author: UraionLabs

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e is an open-source language model by UraionLabs. Features: 8b LLM, VRAM: 8.9GB, License: other.

8-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 Mlx Mlx-lm Mlx-vlm Nemotron Nemotron-3.5 Nemotron-bolt Nl No Nvidia Omlx On-device Oq Oq8e 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-oQ8e

NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e Parameters and Internals

LLM Name	NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e
Repository 🤗	https://huggingface.co/UraionLabs/NVIDIA-Nemotron-3.5-Bolt-E4B-MLX-oQ8e
Base Model(s)	nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
Model Size	8b
Required VRAM	8.9 GB
Updated	2026-10-27
Maintainer	UraionLabs
Model Type	gemma4
Model Files	5.0 GB: 1-of-2 3.9 GB: 2-of-2
Supported Languages	en 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 Architecture	Gemma4ForConditionalGeneration
License	other
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to NVIDIA Nemotron 3.5 Bolt E4B MLX OQ8e

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 E4B It	0K / 16 GB	4027807	1785
Gemma 4 E4B It	0K / 16 GB	229908	23
...DIA Nemotron 3.5 Bolt E4B BF16	0K / 15.9 GB	3418	56
Gemma 4 E4B	0K / 16 GB	268109	386
Lite OmniJev	0K / 32.1 GB	184	1
Vishwamai Stage1	0K / 16 GB	472	0
Linne Sprout 1 0	0K / 16 GB	35	1
Gemma 4 E4B It FP8 Dynamic	0K / 12 GB	31	1
Gemma4 E4B 8B Heretic Ultra	0K / 16 GB	98	0
Gemma E4B Mt B Split3	0K / 16 GB	98	0

Note: green Score (e.g. "73.2") means that the model is better than UraionLabs/NVIDIA-Nemotron-3.5-Bolt-E4B-MLX-oQ8e.