What are the hardware requirements for RedPajama INCITE Instruct 3B V1?

RedPajama INCITE Instruct 3B V1 requires approximately 5.7 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed RedPajama INCITE Instruct 3B V1 and how large is it?

RedPajama INCITE Instruct 3B V1 is developed by togethercomputer, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does RedPajama INCITE Instruct 3B V1 perform on standard benchmarks?

RedPajama INCITE Instruct 3B V1 has the following published scores: MMLU 25.99. Compare against reference models on this page or on the LLM Explorer leaderboards.

RedPajama INCITE Instruct 3B V1 by togethercomputer — VRAM 5.7GB, 2K context

Name: RedPajama INCITE Instruct 3B V1
Author: togethercomputer

RedPajama INCITE Instruct 3B V1 is an open-source language model by togethercomputer. Features: 3b LLM, VRAM: 5.7GB, Context: 2K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.13, Arc: 42.6, HellaSwag: 67.5, MMLU: 26, GSM8K: 0.9.

Dataset:muennighoff/natural-in... Dataset:muennighoff/p3 Dataset:togethercomputer/redpa... Deploy:sagemaker En Endpoints compatible Fp16 Gpt neox Instruct Pytorch Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1

RedPajama INCITE Instruct 3B V1 Parameters and Internals

Model Type

language model

Additional Notes

The model may not be suitable for use in safety-critical applications or for making decisions with significant impacts.

Supported Languages

en (proficient)

Training Details

Data Sources:

togethercomputer/RedPajama-Data-1T

Data Volume:

131M tokens

Methodology:

Fine-tuned for few-shot applications with exclusion of tasks that overlap with the HELM core scenarios

Hardware Used:

8 A100 GPUs

LLM Name	RedPajama INCITE Instruct 3B V1
Repository 🤗	https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1
Base Model(s)	Guanaco 3B Uncensored V2 LoRA Fredithefish/Guanaco-3B-Uncensored-v2-LoRA
Model Size	3b
Required VRAM	5.7 GB
Updated	2026-07-31
Maintainer	togethercomputer
Model Type	gpt_neox
Instruction-Based	Yes
Model Files	5.7 GB
Supported Languages	en
Quantization Type	fp16
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50432
Torch Data Type	float16

Rank the RedPajama INCITE Instruct 3B V1 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 RedPajama INCITE Instruct 3B V1

Best Alternatives	Context / RAM	Downloads	Likes
Stablecode Instruct Alpha 3B	4K / 6.1 GB	2	304
...blecode Instruct Alpha 3B GPTQ	4K / 1.8 GB	10	17
...blecode Instruct Alpha 3B GPTQ	4K / 1.8 GB	5	1
...ama INCITE Chat Instruct 3B V1	2K / 5.5 GB	55	1
... Instruction Tuning With GPT 4	2K / 5.7 GB	134	3
Koishi Instruct 3B	2K / 5.7 GB	54	3
...ama INCITE Instruct 3B V1 GGML	2K / 1.7 GB	8	10
Text2table	2K / 5.7 GB	10	4