What are the hardware requirements for Nemotron 15B Thinker Instruct?

Nemotron 15B Thinker Instruct requires approximately 29.9 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nemotron 15B Thinker Instruct and how large is it?

Nemotron 15B Thinker Instruct is developed by Nitral-Archive, a model with 15b 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 Nemotron 15B Thinker Instruct?

Nemotron 15B Thinker Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nemotron 15B Thinker Instruct by Nitral-Archive — VRAM 29.9GB, 64K context

Name: Nemotron 15B Thinker Instruct
Author: Nitral-Archive

Nemotron 15B Thinker Instruct is an open-source language model by Nitral-Archive. Features: 15b LLM, VRAM: 29.9GB, Context: 64K, License: other, Instruction-Based, LLM Explorer Score: 0.18.

En Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Nitral-Archive/Nemotron-15b-Thinker-instruct

Nemotron 15B Thinker Instruct Parameters and Internals

LLM Name	Nemotron 15B Thinker Instruct
Repository 🤗	https://huggingface.co/Nitral-Archive/Nemotron-15b-Thinker-instruct
Model Size	15b
Required VRAM	29.9 GB
Updated	2026-04-23
Maintainer	Nitral-Archive
Model Type	mistral
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-7 4.9 GB: 2-of-7 4.9 GB: 3-of-7 4.9 GB: 4-of-7 4.9 GB: 5-of-7 4.1 GB: 6-of-7 1.3 GB: 7-of-7
Supported Languages	en
Model Architecture	MistralForCausalLM
License	other
Context Length	65536
Model Max Length	65536
Transformers Version	4.51.3
Tokenizer Class	PreTrainedTokenizer
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Nemotron 15B Thinker Instruct 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 Nemotron 15B Thinker Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Sol Reaver 15B Instruct	64K / 29.9 GB	16	15
Mistral 15B Instruct V0.1	32K / 28.4 GB	79	0

Note: green Score (e.g. "73.2") means that the model is better than Nitral-Archive/Nemotron-15b-Thinker-instruct.