K EXAONE 152B A23B REAP 80E BF16 V2 is an open-source language model by Baekpica. Features: 152b LLM, VRAM: 302.9GB, Context: 256K, License: other, LLM Explorer Score: 0.31.
Base model:baekpica/k-exaone-1... Base model:finetune:baekpica/k... Conversational De En Endpoints compatible Es Exaone Exaone moe Ja K-exaone Ko Lg-ai Moe Post-training Pruning Reap Region:us Safetensors Sharded Tensorflow Vi
Model Card on HF 🤗: https://huggingface.co/Baekpica/K-EXAONE-152B-A23B-REAP-80E-BF16-v2
K EXAONE 152B A23B REAP 80E BF16 V2 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
K EXAONE 152B A23B REAP 80E BF16 V2 Parameters and Internals
| LLM Name | K EXAONE 152B A23B REAP 80E BF16 V2 |
| Repository 🤗 | https://huggingface.co/Baekpica/K-EXAONE-152B-A23B-REAP-80E-BF16-v2 |
| Base Model(s) | |
| Model Size | 152b |
| Required VRAM | 302.9 GB |
| Updated | 2026-07-12 |
| Maintainer | Baekpica |
| Model Type | exaone_moe |
| Model Files | |
| Supported Languages | en ko es de ja vi |
| Model Architecture | ExaoneMoEForCausalLM |
| License | other |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 5.13.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 153600 |
| Errors | replace |
Rank the K EXAONE 152B A23B REAP 80E BF16 V2 Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 55029 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a