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

RedPajama INCITE Instruct 3B V1 GGML requires approximately 1.7 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 GGML and how large is it?

RedPajama INCITE Instruct 3B V1 GGML is developed by keldenl, 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 GGML perform on standard benchmarks?

RedPajama INCITE Instruct 3B V1 GGML 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 GGML by keldenl — VRAM 1.7GB, 2K context

Name: RedPajama INCITE Instruct 3B V1 GGML
Author: keldenl

RedPajama INCITE Instruct 3B V1 GGML is an open-source language model by keldenl. Features: 3b LLM, VRAM: 1.7GB, Context: 2K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.11, Arc: 42.6, HellaSwag: 67.5, MMLU: 26, GSM8K: 0.9.

Dataset:muennighoff/natural-in... Dataset:muennighoff/p3 Dataset:togethercomputer/redpa... En Endpoints compatible Fp16 Ggml Gpt neox Instruct Q4 Quantized Red pajama Region:us

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

RedPajama INCITE Instruct 3B V1 GGML Parameters and Internals

Model Type

Language Model

Additional Notes

The model was fine-tuned for few-shot applications and does not work with llama.cpp as of 5/13/2023 but works with the GGML via gpt-neox.

Supported Languages

en (proficient)

Input Output

Input Format:

Instruction format + few shot prompting

LLM Name	RedPajama INCITE Instruct 3B V1 GGML
Repository 🤗	https://huggingface.co/keldenl/RedPajama-INCITE-Instruct-3B-v1-GGML
Base Model(s)	...ama INCITE Chat Instruct 3B V1 acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
Model Size	3b
Required VRAM	1.7 GB
Updated	2026-07-17
Maintainer	keldenl
Model Type	gpt_neox
Instruction-Based	Yes
Model Files	1.7 GB 2.1 GB
Supported Languages	en
GGML Quantization	Yes
Quantization Type	fp16\|ggml\|q4
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 GGML 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 GGML

Best Alternatives	Context / RAM	Downloads	Likes
...edPajama INCITE Instruct 3B V1	2K / 5.7 GB	280	93
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
Text2table	2K / 5.7 GB	10	4

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