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

RedPajama INCITE Chat 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 Chat 3B V1 and how large is it?

RedPajama INCITE Chat 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 Chat 3B V1 perform on standard benchmarks?

RedPajama INCITE Chat 3B V1 has the following published scores: MMLU 26.23. Compare against reference models on this page or on the LLM Explorer leaderboards.

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

Name: RedPajama INCITE Chat 3B V1
Author: togethercomputer

RedPajama INCITE Chat 3B V1 is an open-source language model by togethercomputer. Features: 3b LLM, VRAM: 5.7GB, Context: 2K, License: apache-2.0, Quantized, LLM Explorer Score: 0.12, Arc: 42.8, HellaSwag: 67.6, MMLU: 26.2, GSM8K: 0.5.

Dataset:databricks/databricks-... Dataset:openassistant/oasst1 Dataset:togethercomputer/redpa... Deploy:azure Deploy:sagemaker En Endpoints compatible Fp16 Gpt neox Pytorch Quantized Region:us

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

RedPajama INCITE Chat 3B V1 Parameters and Internals

Model Type

Language Model

Use Cases

Areas:

Chatting

Limitations:

Not suitable for safety-critical applications, May not perform well for complex or ambiguous questions

Considerations:

End users should be aware of the limitations and ensure responsible use.

Supported Languages

English (high)

Training Details

Data Sources:

togethercomputer/RedPajama-Data-1T

Data Volume:

131M tokens

Methodology:

Fine-tuned on OASST1 and Dolly2 to enhance chatting ability

Hardware Used:

8 A100 GPUs

Input Output

Input Format:

Prompt requires `: [Instruction] :` format

Accepted Modalities:

Text

Output Format:

Text

LLM Name	RedPajama INCITE Chat 3B V1
Repository 🤗	https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1
Base Model(s)	RedPajama INCITE Vicuna 3B V1 RootYuan/RedPajama-INCITE-Vicuna-3B-v1
Model Size	3b
Required VRAM	5.7 GB
Updated	2026-08-05
Maintainer	togethercomputer
Model Type	gpt_neox
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 Chat 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 Chat 3B V1

Best Alternatives	Context / RAM	Downloads	Likes
Stablelm Tuned Alpha 3B 8bit	4K / 4.3 GB	14	3
Stablelm Tuned Alpha 3B 16bit	4K / 7.5 GB	13	6
...edPajama INCITE Instruct 3B V1	2K / 5.7 GB	280	93
Bling Red Pajamas 3B 0.1	2K / 5.5 GB	9	5
Twinsights 3b Alpha 8bit	2K / 3.2 GB	5	0
Dolly V2 3B 8bit	2K / 3.2 GB	6	0
Stablecode Completion Alpha 3B	16K / 14.1 GB	180	119
RedPajama 3B 16384	16K / 19.7 GB	10	4
Redpajama 3B Chat	5K / 6.4 GB	13	2
Stablelm Base Alpha 3B	4K / 14.9 GB	3139	82

Note: green Score (e.g. "73.2") means that the model is better than togethercomputer/RedPajama-INCITE-Chat-3B-v1.