What are the hardware requirements for Kepler 8B Instruct V2?

Kepler 8B Instruct V2 requires approximately 15.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kepler 8B Instruct V2 and how large is it?

Kepler 8B Instruct V2 is developed by intellectlabs, a model with 8b 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 Kepler 8B Instruct V2?

Kepler 8B Instruct V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kepler 8B Instruct V2 by intellectlabs — VRAM 15.4GB, 32K context

Name: Kepler 8B Instruct V2
Author: intellectlabs

Kepler 8B Instruct V2 is an open-source language model by intellectlabs. Features: 8b LLM, VRAM: 15.4GB, Context: 32K, License: apache-2.0, Instruction-Based, Merged, LLM Explorer Score: 0.25.

Merged Model Base model:finetune:intellectl... Base model:intellectlabs/keple... Conversational En Gguf Instruct Llama.cpp Quantized Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/intellectlabs/Kepler-8B-Instruct-v2

Kepler 8B Instruct V2 Parameters and Internals

LLM Name	Kepler 8B Instruct V2
Repository 🤗	https://huggingface.co/intellectlabs/Kepler-8B-Instruct-v2
Base Model(s)	Kepler 8B Instruct V2 intellectlabs/Kepler-8B-Instruct-v2
Merged Model	Yes
Model Size	8b
Required VRAM	15.4 GB
Updated	2026-07-20
Maintainer	intellectlabs
Model Type	qwen2
Instruction-Based	Yes
Model Files	1.1 GB: 1-of-9 2.0 GB: 2-of-9 1.9 GB: 3-of-9 1.9 GB: 4-of-9 1.9 GB: 5-of-9 1.9 GB: 6-of-9 1.9 GB: 7-of-9 1.9 GB: 8-of-9 0.9 GB: 9-of-9
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	5.0.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151665
Errors	replace

Rank the Kepler 8B Instruct V2 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 Kepler 8B Instruct V2

Best Alternatives	Context / RAM	Downloads	Likes
Sailor2 8B Chat	4K / 17.1 GB	661	19
Sailor2 8B Chat Uncensored	32K / 17.1 GB	90	2