What are the hardware requirements for NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit?

NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit requires approximately 43.1 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit and how large is it?

NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit is developed by Duckets, a model with 74b 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 74B A9B MLX 4bit?

NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit 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 74B A9B MLX 4bit by Duckets — VRAM 43.1GB, 256K context

Name: NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit
Author: Duckets

NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit is an open-source language model by Duckets. Features: 74b LLM, VRAM: 43.1GB, Context: 256K, License: other, Quantized, LLM Explorer Score: 0.33.

4-bit 4bit Apple-silicon Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv... Conversational Custom code De En Es Fr Image-text-to-text It Ja Lm-studio Mlx Mlx-vlm Moe Nemotron Nemotron-h Nemotron h omni Quantized Region:us Safetensors Sharded Tensorflow Vision

Model Card on HF 🤗: https://huggingface.co/Duckets/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bit

NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit Parameters and Internals

LLM Name	NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit
Repository 🤗	https://huggingface.co/Duckets/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bit
Base Model(s)	nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
Model Size	74b
Required VRAM	43.1 GB
Updated	2026-10-20
Maintainer	Duckets
Model Type	nemotron_h_omni
Model Files	5.2 GB: 1-of-9 5.0 GB: 2-of-9 5.3 GB: 3-of-9 4.7 GB: 4-of-9 5.3 GB: 5-of-9 5.2 GB: 6-of-9 5.3 GB: 7-of-9 5.3 GB: 8-of-9 1.8 GB: 9-of-9
Supported Languages	en es fr de it ja
Quantization Type	4bit
Model Architecture	NemotronH_Omni_Reasoning_V3
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	5.8.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|im_end\|>

Rank the NVIDIA Nemotron 3.5 Bolt 74B A9B MLX 4bit 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 74B A9B MLX 4bit

Best Alternatives	Context / RAM	Downloads	Likes
...Nemotron 3.5 Bolt 74B A9B 24GB	0K / 8.8 GB	6060	129
...tron 3.5 Bolt 74B A9B EXL3 2.5	0K / 27.6 GB	180	1
...tron 3.5 Bolt 74B A9B EXL3 2.0	0K / 23.4 GB	179	1
...tron 3.5 Bolt 74B A9B EXL3 3.0	0K / 31.6 GB	177	1
...tron 3.5 Bolt 74B A9B EXL3 3.5	0K / 35.7 GB	176	1
...tron 3.5 Bolt 74B A9B EXL3 6.0	0K / 58.3 GB	176	1
...tron 3.5 Bolt 74B A9B EXL3 4.0	0K / 39.9 GB	174	1
...tron 3.5 Bolt 74B A9B EXL3 5.0	0K / 49.1 GB	174	1

Note: green Score (e.g. "73.2") means that the model is better than Duckets/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bit.