Vangelus Secundus is an open-source language model by ClaudioItaly. Features: 9b LLM, VRAM: 18.6GB, Context: 8K, Merged, LLM Explorer Score: 0.18.
Merged Model Arxiv:2306.01708 Base model:claudioitaly/1800-9... Base model:ifable/gemma-2-ifab... Base model:sam-paech/delirium-... Conversational Endpoints compatible Gemma2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ClaudioItaly/Vangelus-Secundus
Vangelus Secundus 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)
Vangelus Secundus Parameters and Internals
| LLM Name | Vangelus Secundus |
| Repository 🤗 | https://huggingface.co/ClaudioItaly/Vangelus-Secundus |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 9b |
| Required VRAM | 18.6 GB |
| Updated | 2026-04-09 |
| Maintainer | ClaudioItaly |
| Model Type | gemma2 |
| Model Files | |
| Model Architecture | Gemma2ForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to Vangelus Secundus
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| G2 GSHT 32K | 32K / 20.4 GB | 6 | 1 |
| SystemGemma2 9B It | 32K / 18.6 GB | 6 | 2 |
| GWQ 9B Preview2 | 8K / 18.6 GB | 13 | 10 |
| Gemma 2 9B It | 8K / 18.6 GB | 262937 | 781 |
| Gemma 2 9B It | 8K / 18.6 GB | 6 | 0 |
| Gemma 2 9B It SimPO | 8K / 18.6 GB | 410 | 172 |
| Turkish Gemma 9B T1 | 8K / 18.6 GB | 49652 | 175 |
| Gemma 2 9B | 8K / 37.1 GB | 83831 | 672 |
| Gemma 2 9B It Advanced V2.1 | 8K / 20.4 GB | 4 | 28 |
| ...erge 02012025163610 Gemma 2 9B | 8K / 20.4 GB | 53 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ClaudioItaly/Vangelus-Secundus .
Rank the Vangelus Secundus 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? 52721 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