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: 0.27.
| LLM Name | Kepler 8B Instruct V2 |
| Repository 🤗 | https://huggingface.co/intellectlabs/Kepler-8B-Instruct-v2 |
| Base Model(s) | |
| 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 | |
| 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 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Sailor2 8B Chat | 4K / 17.1 GB | 682 | 19 |
| Sailor2 8B Chat Uncensored | 32K / 17.1 GB | 2 | 2 |
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟