Ettin Decoder 68M is an open-source language model by jhu-clsp. Features: 68m LLM, VRAM: 0.3GB, Context: 7K, License: mit, LLM Explorer Score: 0.2.
Model Card on HF 🤗: https://huggingface.co/jhu-clsp/ettin-decoder-68m
Ettin Decoder 68M 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)
Ettin Decoder 68M Parameters and Internals
| LLM Name | Ettin Decoder 68M |
| Repository 🤗 | https://huggingface.co/jhu-clsp/ettin-decoder-68m |
| Model Size | 68m |
| Required VRAM | 0.3 GB |
| Updated | 2026-07-02 |
| Maintainer | jhu-clsp |
| Model Type | modernbert-decoder |
| Model Files | |
| Supported Languages | en |
| Model Architecture | ModernBertDecoderForCausalLM |
| License | mit |
| Context Length | 7999 |
| Model Max Length | 7999 |
| Transformers Version | 4.47.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | [PAD] |
| Vocabulary Size | 50368 |
| Torch Data Type | float32 |
Rank the Ettin Decoder 68M 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? 54964 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